Not in the top 1,000 by GitHub stars
JHostalek/dotclaude
Agent skills for agentic coding tools. Extremely opinionated. Updated (almost) daily.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/audit/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1ca181388ad3
No earlier version was observed for comparison.
skills/design/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1ca181388ad3
No earlier version was observed for comparison.
skills/distill/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1ca181388ad3
No earlier version was observed for comparison.
skills/git-workflow/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1ca181388ad3
No earlier version was observed for comparison.
skills/intent-brief/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1ca181388ad3
No earlier version was observed for comparison.
skills/judge/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1ca181388ad3
No earlier version was observed for comparison.
skills/query-refiner/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1ca181388ad3
No earlier version was observed for comparison.
skills/sota/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1ca181388ad3
No earlier version was observed for comparison.
skills/timesheet/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1ca181388ad3
No earlier version was observed for comparison.
skills/writing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1ca181388ad3
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit 1ca181388ad315d332cf0de07ea5fd1b3ccb8372
git clone --filter=blob:none --no-checkout https://github.com/JHostalek/dotclaude.git .hotskills/jhostalek-dotclaude && git -C .hotskills/jhostalek-dotclaude checkout --detach 1ca181388ad315d332cf0de07ea5fd1b3ccb8372
# Copy each selected skill directory from .hotskills/jhostalek-dotclaude into .claude/skills/<skill-name>/11GitHub stars
0stars in 7 days
10skills in this repository
15commits in 30 days
Heat
1.6- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- audit
skills/audit - design
skills/design - distill
skills/distill - git-workflow
skills/git-workflow - intent-brief
skills/intent-brief - judge
skills/judge - query-refiner
skills/query-refiner - sota
skills/sota - timesheet
skills/timesheet - writing
skills/writing
How it works
audit
When your agent uses it
Review code through focused dimensions, with one independent agent per dimension.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
160 tokensWhen the skill is activated
Reference documents
26,772 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../.claude-plugin/marketplace.jsonasset558 bytes../../.claude-plugin/plugin.jsonasset756 bytesSKILL.mdcore744 bytesagents/openai.yamlasset43 bytesreferences/abstractions.mddoc1,580 bytesreferences/comments.mddoc2,352 bytesreferences/complexity.mddoc2,520 bytesreferences/consistency.mddoc1,237 bytesreferences/contracts.mddoc1,914 bytesreferences/correctness.mddoc1,867 bytesreferences/data-integrity.mddoc2,216 bytesreferences/error-handling.mddoc2,753 bytesreferences/interfaces.mddoc2,241 bytesreferences/logs.mddoc1,525 bytesreferences/modularity.mddoc4,027 bytesreferences/naming.mddoc1,244 bytesreferences/necessity.mddoc1,831 bytesreferences/performance.mddoc2,965 bytesreferences/reliability.mddoc2,090 bytesreferences/security.mddoc2,596 bytesreferences/tests.mddoc1,969 bytesreferences/ux.mddoc1,891 bytesreferences/workflow.mddoc3,047 bytes../design/SKILL.mddoc2,621 bytes../design/agents/openai.yamlasset43 bytes../distill/SKILL.mddoc1,633 bytes../distill/agents/openai.yamlasset153 bytes../git-workflow/SKILL.mddoc1,446 bytes../git-workflow/agents/openai.yamlasset42 bytes../git-workflow/references/commit.mddoc867 bytes../git-workflow/references/conventional-commits.mddoc972 bytes../git-workflow/references/integration.mddoc1,237 bytes../git-workflow/references/pr.mddoc3,076 bytes../git-workflow/references/ship.mddoc2,260 bytes../intent-brief/SKILL.mddoc1,235 bytes../intent-brief/agents/openai.yamlasset43 bytes../judge/SKILL.mddoc1,654 bytes../judge/agents/openai.yamlasset43 bytes../query-refiner/SKILL.mddoc1,901 bytes../sota/SKILL.mddoc496 bytes../sota/agents/openai.yamlasset207 bytes../timesheet/SKILL.mddoc1,403 bytes../timesheet/agents/openai.yamlasset43 bytes../writing/SKILL.mddoc3,316 bytes../writing/agents/openai.yamlasset148 bytes../writing/references/README.mddoc7,846 bytes../writing/references/cs-pairs.mddoc34,045 bytes../writing/references/tells.mddoc5,535 bytes
Read SKILL.md
Audit `$ARGUMENTS` per [the review workflow](references/workflow.md): one reviewer per dimension, each over the whole requested scope. Read-only: report findings, change no code.
Dimensions, one file each in `references/`: abstractions, comments, complexity, consistency, contracts, correctness, data-integrity, error-handling, interfaces, logs, modularity, naming, necessity, performance, reliability, security, tests, ux.
Examples: `/audit modularity`, `/audit contracts security src/auth`, `/audit necessity`, `/audit full`, `/audit ux /settings`.design
When your agent uses it
Explore competing approaches through independent agents before selecting an implementation.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
475 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore2,621 bytesagents/openai.yamlasset43 bytes
Read SKILL.md
Explore `$ARGUMENTS` and produce approaches with distinct core mechanisms. Use the smallest useful set of independent explorers; add one only to cover a material alternative or unresolved gap. If delegation is unavailable, disclose that limit and explore sequentially without claiming independence.
Establish the raw problem, actual constraints, and obvious solutions. Reframe where it exposes a different mechanism; do not force reframing for a bounded problem. Give explorers the same relevant repository context, their chosen method, and a distinct question or provocation. They must not see each other's proposals. Reframings are optional starting points, not constraints. Send revisions back to their authors.
Choose methods that expose different mechanisms; this is a menu, not required coverage:
| Method | Approach and check |
| --- | --- |
| Build upward | Start with the smallest useful unit; check emergent needs and necessary upfront investment. |
| Work backward | Derive prerequisites from the ideal outcome; check the path is buildable. |
| Constraint first | Solve or dissolve the hardest constraints; preserve the user outcome. |
| Transfer an analogy | Borrow a mechanism from another domain; identify where the analogy breaks. |
| Eliminate | Remove parts while preserving value; account for interactions and useful polish. |
| Adversarial | Design around consequential failures; state the cost of robustness. |distill
When your agent uses it
Distill rough text into dense, expert-register English where terms of art carry the intent.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
373 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,633 bytesagents/openai.yamlasset153 bytes
Read SKILL.md
# Distill
Distill the target (my text, a named file, or else my previous message) into expert-register English. I write in a second language; you hold the vocabulary I lack. Elevate to it.
The reader is a domain expert or a model. A **term of art** is the established word practitioners use for a concept: it carries a sentence or a paragraph of intent and recruits the reader's priors for free.
1. **Intent**: list every claim, constraint, exclusion, name, and branch in the original. Done when each original sentence maps to an item.
2. **Distill**: name each item with its term of art, then write the shortest text that carries the whole list. Cut restatement, hedging, and explanatory scaffolding. Choose the term practitioners actually use over the rarer synonym: precision, not ornament. Reject a term whose home-domain connotation pulls the wrong way. Keep my names, numbers, and stance.
3. **Back-translate**: give a cold-reader subagent the draft alone and ask it to restate the intent as a list. Diff that against step 1; each missing or drifted item is a loss to fix. Done when the lists match, or two rounds have run. Without subagents, expand each term yourself against step 1.
4. **Return**: the distilled text, then a glossary of each term you introduced and the meaning it replaced, so I learn it. When the target is a file, apply the rewrite there and report the word count before and after.git-workflow
When your agent uses it
Apply personal Git conventions when committing, creating or updating PRs, merging, rebasing, or explicitly shipping work end to end.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
296 tokensWhen the skill is activated
Reference documents
1,774 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,446 bytesagents/openai.yamlasset42 bytesreferences/commit.mddoc867 bytesreferences/conventional-commits.mddoc972 bytesreferences/integration.mddoc1,237 bytesreferences/pr.mddoc3,076 bytesreferences/ship.mddoc2,260 bytes
Read SKILL.md
Use the mode requested by the user or calling skill. A request for a commit message only produces a message; an ordinary commit or PR request does not authorize merging. Honor narrower instructions already given.
Read the relevant reference before acting:
| Mode | Reference |
| --- | --- |
| Commit or commit message | [commit.md](references/commit.md) |
| Create or update a PR/MR | [pr.md](references/pr.md) |
| Merge a branch, rebase, or resolve conflicts | [integration.md](references/integration.md) |
| Explicit end-to-end shipping | [ship.md](references/ship.md) |
Use the intended repository, current branch, and remote. Preserve unrelated work and staged changes. One PR per repository; update an existing PR for the branch.
Ordinary commit mode commits locally. PR mode includes pushing the relevant commits. Explicit branch-merge and rebase modes include publishing the result, using a lease for a rewritten remote branch. End-to-end mode includes implementation, verification, commit, push, PR creation/update, merge, and remote source-branch deletion.intent-brief
When your agent uses it
Evidence-first intent elicitation. Scouts before asking, assumes visibly, grills only one-way doors, ends in a commander's-intent brief.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
266 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,235 bytesagents/openai.yamlasset43 bytes
Read SKILL.md
Elicit my intent with minimal interrogation; my attention is the scarce resource.
1. Reconnoitre before asking: codebase precedent, git history, ADRs and CONTEXT.md, prior conversations, upstream docs, the web. Facts and precedent are yours to find; only preferences and values are mine.
2. Present an assumption ledger. Default on two-way doors; management by exception, silence is consent.
3. Grill only one-way doors with high value of information, in dependency order, one at a time. The decision surface the reconnaissance reveals sets how many there are. Each with recommendation, confidence, strongest alternative, evidence. Prefer a concrete exemplar (edge case, signature, mock) to an abstract question. Defer the rest to the last responsible moment.
4. Run a brief pre-mortem.
5. Stop when residual VOI is negligible. Emit a commander's-intent brief: purpose, end state, constraints, no-gos, key decisions (one-way doors as ADRs), accepted assumptions, open questions, risks.
Do not act until I confirm the brief.judge
When your agent uses it
Obtain an independent review of the approach and trade-offs in completed work.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
292 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,654 bytesagents/openai.yamlasset43 bytes
Read SKILL.md
Review `$ARGUMENTS`, or the latest substantive work when omitted. Infer scope from the conversation and relevant files; ask only if ambiguity would materially change the review.
Delegate to one independent, read-only reviewer with a clean context: the requested outcome, constraints, subject, relevant files, stack, and project conventions. Do not provide your verdict or preferred critique. Add reviewers only for materially distinct expertise. If delegation is unavailable, disclose that limitation; do not call self-review independent.
Ask the reviewer to assess domain fitness, architectural choices, proportionality, and fundamentally different ways to achieve the outcome. Distinguish justified deviations from missed constraints; compare simplicity against real requirements and account for the adoption costs of alternatives. Feature necessity is a separate lens available through `/audit necessity`, not an automatic additional pass.
Retain findings supported by specific evidence, an actionable alternative, and its costs. Distinguish defects, valid trade-offs, and preferences. Remove claims that misread constraints or lack evidence; preserve meaningful disagreements if multiple reviewers were used.
Report a clear recommendation and its rationale, validated strengths, findings by importance, and the single most valuable change, if any. Identify missing evidence and reviewer limitations. Stop after the report; implement only when asked.query-refiner
When your agent uses it
Refine a supplied question into a precise, expert-level query when the user asks to rewrite or optimize their question or prompt. Do not use to answer the underlying question.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
410 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,901 bytes
Read SKILL.md
# Query Refiner
Rewrite the user's rough input in expert register to elicit a stronger LLM response. Reformulate only; never answer, execute, or comment on it.
Expert register recruits the target model's domain priors. Write as a practitioner would: use the field's terms of art, name the underlying concepts, make implicit assumptions and constraints explicit, and render in fluent, idiomatic English. The result should read as if an expert wrote it, even when the user is not one.
- **Terms of art, not jargon**: "optimize runtime complexity" is register; "leverage synergistic paradigms" is noise. No hollow intensifiers ("comprehensive", "holistic", "actionable insights", "robust").
- **Fidelity**: translate, don't reinterpret. Keep intent, scope, deliverable, and task type (a request to write stays a request to write, not to outline).
- **Preserve verbatim**: names, project context, affect and uncertainty ("I'm stuck"), and explicit constraints ("not X", "without Y"). Never genericize.
- **Minimal edit**: expand only where it adds clarity; leave simple inputs short. Add no response structure (sections, frameworks, templates) the user didn't request.
By input type:
- Question: tighten scope and terminology.
- Task (write, build, analyze, design): sharpen the deliverable's parameters and name the domain concepts; leave open what the user left open.sota
When your agent uses it
Produce an up-to-date, state-of-the-art recommendation using domain expertise and web research. Use only when explicitly invoked.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
93 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore496 bytesagents/openai.yamlasset207 bytes
Read SKILL.md
# SOTA
Draw on your existing domain knowledge, including established practices and known failure modes from others’ implementations. Search the web for current state-of-the-art approaches, industry standards, and how others solve this problem. Recommend the best solution for this specific context.timesheet
When your agent uses it
Prepare monthly timesheet entries from Git commits.
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
292 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Data Collection
- Output Format
- Summary Style
Files
SKILL.mdcore1,403 bytesagents/openai.yamlasset43 bytes
Read SKILL.md
Generate a markdown table of the current user's git commits for the requested month, defaulting to the current month.
## Data Collection
Repo in working directory. Scope: requested month, defaulting to the current month (1st → now), current user only — filter by `git config user.name`.
Use local calendar boundaries: midnight on the first day of the requested month through the current time, or the next month’s midnight for a completed month. Calculate dates with calendar-aware arithmetic. Filter the author name literally and exclude merge commits; never construct an invalid date by incrementing the day number.
## Output Format
Markdown table, one row per day with commits:
| Day | Summary |
|-----|---------|writing
When your agent uses it
Rewrite slop, or a reply that did not land, into text a person would write.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
752 tokensWhen the skill is activated
Reference documents
14,267 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Find the reader
- 2. Study the pairs (Czech)
- 3. Rewrite
- 4. Review
- 5. Return
Files
SKILL.mdcore3,316 bytesagents/openai.yamlasset148 bytesreferences/README.mddoc7,846 bytesreferences/cs-pairs.mddoc34,045 bytesreferences/tells.mddoc5,535 bytes
Read SKILL.md
# Writing
Rewrite the given text or passage as a person would write it. With no target, rewrite the last substantive agent response. Ask only when the target or intended meaning cannot be determined.
**Slop** is text that reads as generated: padded, generic, inflated, shaped by habits no person would choose. Each habit is a **tell**. [`references/tells.md`](references/tells.md) catalogs tells for the reviewer. The writer works from the positive targets below, not the catalog.
## 1. Find the reader
Name the reader, what they already know, and what they must do or decide after reading. Find where the original loses them: a buried point, missing context, an unexplained term, slop. For project text, use the domain terms in the repo glossary (`GLOSSARY.md`, or `CONTEXT.md` in older repos).
Done when you can state the reader's need and the original's failure in one sentence each.
## 2. Study the pairs (Czech)
Skills included
- audit
- design
- distill
- git-workflow
- intent-brief
- judge
- query-refiner
- sota
- timesheet
- writing
Repository facts
- License
- CC0-1.0
- Created
- Mar 3, 2026
- Last pushed
- Nov 3, 2026
- Forks
- 5
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
- No broad tool permissions
- No dangerous shell commands
- 69 network referencesin 6 files: skills/writing/references/README.md:17 skills/writing/references/cs-pairs.md:12 .claude-plugin/plugin.json:5 and 3 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 69 signals by file
.claude-plugin/marketplace.json
.claude-plugin/plugin.json
- Network accessline 5
"author": { "name": "Jan Hostalek", "url": "https://github.com/JHostalek" - Network accessline 6
"name": "Jan Hostalek", "url": "https://github.com/JHostalek" }, - Network accessline 7
"url": "https://github.com/JHostalek" - Network accessline 8
}, "homepage": "https://github.com/JHostalek/dotclaude", "repository": "https://github.com/JHostalek/dotclaude", - Network accessline 9
"homepage": "https://github.com/JHostalek/dotclaude", - Network accessline 10
"repository": "https://github.com/JHostalek/dotclaude",
skills/git-workflow/references/conventional-commits.md
skills/git-workflow/references/pr.md
- Network accessline 73
Body template adapted from Matt Pocock's [`pr` skill](https://github.com/mattpocock/skills/tree/main/skills/engineering/pr) (MIT), whose Summary visuals come from Dex Horthy's [`show-me`](https://github.com/humanlayer/skills/blob/main/plugi - Network accessline 73
Body template adapted from Matt Pocock's [`pr` skill](https://github.com/mattpocock/skills/tree/main/skills/engineering/pr) (MIT), whose Summary visuals come from Dex Horthy's [`show-me`](https://github.com/humanlayer/skills/blob/main/plugi
skills/writing/references/README.md
- Network accessline 17
- `osm-odstavka-api`: „[Talk-cz] Odstávka api.openstreetmap.org“, https://lists.openstreetmap.org/pipermail/talk-cz/2016-May/014117.html, Marián Kyral, mailing list talk-cz, 9. 5. 2016. Lidské autorství: datovaný příspěvek v archivu mailing - Network accessline 17
- `osm-odstavka-api`: „[Talk-cz] Odstávka api.openstreetmap.org“, https://lists.openstreetmap.org/pipermail/talk-cz/2016-May/014117.html, Marián Kyral, mailing list talk-cz, 9. 5. 2016. Lidské autorství: datovaný příspěvek v archivu mailing - Network accessline 18
- `osm-sotm-prednasejici`: „[Talk-cz] hledám přednášející na SOTM“, https://lists.openstreetmap.org/pipermail/talk-cz/2018-September/019829.html, Miroslav Suchý, mailing list talk-cz, 13. 9. 2018. Lidské autorství: datovaný příspěvek v arch - Network accessline 18
- `osm-sotm-prednasejici`: „[Talk-cz] hledám přednášející na SOTM“, https://lists.openstreetmap.org/pipermail/talk-cz/2018-September/019829.html, Miroslav Suchý, mailing list talk-cz, 13. 9. 2018. Lidské autorství: datovaný příspěvek v arch - Network accessline 19
- `osm-pivo-online`: „[talk-cz] Kvartální pivo - online“, https://lists.openstreetmap.org/pipermail/talk-cz/2020-December/023053.html, Marián Kyral (podepsáno Marián a Tom), mailing list talk-cz, 1. 12. 2020. Lidské autorství: datovaný přís - Network accessline 19
- `osm-pivo-online`: „[talk-cz] Kvartální pivo - online“, https://lists.openstreetmap.org/pipermail/talk-cz/2020-December/023053.html, Marián Kyral (podepsáno Marián a Tom), mailing list talk-cz, 1. 12. 2020. Lidské autorství: datovaný přís - Network accessline 20
- `kosik-zruseni-objednavky`: e-mail Košík.cz zákazníkům, citovaný v článku „Kolaps na zlatou neděli. E-shopy s potravinami nestíhají doručovat“, https://www.seznamzpravy.cz/clanek/kolaps-na-zlatou-nedeli-e-shopy-s-potravinami-nestihaji-dor - Network accessline 20
- `kosik-zruseni-objednavky`: e-mail Košík.cz zákazníkům, citovaný v článku „Kolaps na zlatou neděli. E-shopy s potravinami nestíhají doručovat“, https://www.seznamzpravy.cz/clanek/kolaps-na-zlatou-nedeli-e-shopy-s-potravinami-nestihaji-dor - Network accessline 21
- `fakturoid-zdrazeni`: „Nové ceny všech tarifů od 1. října“, https://www.fakturoid.cz/blog/2022/08/17/nove-ceny-od-1-rijna, Fakturoid s.r.o., 17. 8. 2022. Lidské autorství: datovaný příspěvek publikovaný před 30. 11. 2022. - Network accessline 21
- `fakturoid-zdrazeni`: „Nové ceny všech tarifů od 1. října“, https://www.fakturoid.cz/blog/2022/08/17/nove-ceny-od-1-rijna, Fakturoid s.r.o., 17. 8. 2022. Lidské autorství: datovaný příspěvek publikovaný před 30. 11. 2022. - Network accessline 22
- `fakturoid-ucetni`: úvodní stránka Fakturoid.cz, sekce „Spokojená účetní“, https://web.archive.org/web/20211218174014/https://www.fakturoid.cz/, Fakturoid s.r.o., snímek z 18. 12. 2021. Lidské autorství: archivní snímek z doby před 11/202 - Network accessline 22
- `fakturoid-ucetni`: úvodní stránka Fakturoid.cz, sekce „Spokojená účetní“, https://web.archive.org/web/20211218174014/https://www.fakturoid.cz/, Fakturoid s.r.o., snímek z 18. 12. 2021. Lidské autorství: archivní snímek z doby před 11/202 - Network accessline 23
- `fakturoid-trvale-prihlaseni`: „Trvalé přihlášení“, https://www.fakturoid.cz/blog/2018/05/31/trvale-prihlaseni, Fakturoid s.r.o., 31. 5. 2018. Lidské autorství: datovaný příspěvek z doby před 2022. - Network accessline 23
- `fakturoid-trvale-prihlaseni`: „Trvalé přihlášení“, https://www.fakturoid.cz/blog/2018/05/31/trvale-prihlaseni, Fakturoid s.r.o., 31. 5. 2018. Lidské autorství: datovaný příspěvek z doby před 2022. - Network accessline 24
- `slevomat-jak-nakoupit`: „Jak to funguje“, https://web.archive.org/web/20210119212806/https://www.slevomat.cz/jak-to-funguje, Slevomat.cz, snímek z 19. 1. 2021. Lidské autorství: archivní snímek z doby před 11/2022. - Network accessline 24
- `slevomat-jak-nakoupit`: „Jak to funguje“, https://web.archive.org/web/20210119212806/https://www.slevomat.cz/jak-to-funguje, Slevomat.cz, snímek z 19. 1. 2021. Lidské autorství: archivní snímek z doby před 11/2022. - Network accessline 25
- `twisto-jak-to-funguje`: úvodní stránka Twisto.cz, sekce „Jak Twisto funguje?“, https://web.archive.org/web/20201226195416/https://www.twisto.cz/, Twisto payments a.s., snímek z 26. 12. 2020. Lidské autorství: archivní snímek z doby před - Network accessline 25
- `twisto-jak-to-funguje`: úvodní stránka Twisto.cz, sekce „Jak Twisto funguje?“, https://web.archive.org/web/20201226195416/https://www.twisto.cz/, Twisto payments a.s., snímek z 26. 12. 2020. Lidské autorství: archivní snímek z doby před - Network accessline 26
- `erouska-nedorazila-sms`: eRouška pro Android, řetězec `no_verification_caption` v `values-cs/strings.xml`, https://github.com/covid19cz/erouska-android/blob/ef6b4712a798c7b2aa4b91c1dd7d21591eae8fcf/app/src/main/res/values-cs/strings.xml, - Network accessline 26
- `erouska-nedorazila-sms`: eRouška pro Android, řetězec `no_verification_caption` v `values-cs/strings.xml`, https://github.com/covid19cz/erouska-android/blob/ef6b4712a798c7b2aa4b91c1dd7d21591eae8fcf/app/src/main/res/values-cs/strings.xml, - Network accessline 27
- `erouska-rizikove-setkani`: eRouška pro Android, řetězec `exposure_info_text`, stejný soubor a commit jako výše (https://github.com/covid19cz/erouska-android/blob/ef6b4712a798c7b2aa4b91c1dd7d21591eae8fcf/app/src/main/res/values-cs/strings - Network accessline 27
- `erouska-rizikove-setkani`: eRouška pro Android, řetězec `exposure_info_text`, stejný soubor a commit jako výše (https://github.com/covid19cz/erouska-android/blob/ef6b4712a798c7b2aa4b91c1dd7d21591eae8fcf/app/src/main/res/values-cs/strings - Network accessline 28
- `fakturoid-parovani`: "Párování plateb s bankou", Fakturoid podpora, https://web.archive.org/web/20211027152623/https://www.fakturoid.cz/podpora/automatizace/parovani-plateb-s-bankou ; Fakturoid s.r.o.; snímek archivu z 27. 10. 2021, stej - Network accessline 28
- `fakturoid-parovani`: "Párování plateb s bankou", Fakturoid podpora, https://web.archive.org/web/20211027152623/https://www.fakturoid.cz/podpora/automatizace/parovani-plateb-s-bankou ; Fakturoid s.r.o.; snímek archivu z 27. 10. 2021, stej - Network accessline 29
- `seznam-stejna-adresa`: "Časté dotazy k Emailu", oddíl "Někdo má stejnou e-mailovou adresu", Seznam Nápověda, https://web.archive.org/web/20221023080100/https://napoveda.seznam.cz/cz/email/ ; Seznam.cz, a.s.; snímek archivu z 23. 10. 2022 - Network accessline 29
- `seznam-stejna-adresa`: "Časté dotazy k Emailu", oddíl "Někdo má stejnou e-mailovou adresu", Seznam Nápověda, https://web.archive.org/web/20221023080100/https://napoveda.seznam.cz/cz/email/ ; Seznam.cz, a.s.; snímek archivu z 23. 10. 2022 - Network accessline 30
- `seznam-odkazy`: "Nebezpečné odkazy", Seznam Nápověda, https://web.archive.org/web/20211020004942/https://napoveda.seznam.cz/cz/email/nebezpecne-odkazy/ ; Seznam.cz, a.s.; snímek archivu z 20. 10. 2021; důkaz: archivní snímek před 30. 11. - Network accessline 30
- `seznam-odkazy`: "Nebezpečné odkazy", Seznam Nápověda, https://web.archive.org/web/20211020004942/https://napoveda.seznam.cz/cz/email/nebezpecne-odkazy/ ; Seznam.cz, a.s.; snímek archivu z 20. 10. 2021; důkaz: archivní snímek před 30. 11. - Network accessline 31
- `naucse-adresar`: "Nastavení prostředí", Začátečnický kurz PyLadies, naucse.python.cz, https://web.archive.org/web/20210517223645/https://naucse.python.cz/course/pyladies/beginners/venv-setup/ ; autor Petr Viktorin ("Pro PyLadies Brno nap - Network accessline 31
- `naucse-adresar`: "Nastavení prostředí", Začátečnický kurz PyLadies, naucse.python.cz, https://web.archive.org/web/20210517223645/https://naucse.python.cz/course/pyladies/beginners/venv-setup/ ; autor Petr Viktorin ("Pro PyLadies Brno nap - Network accessline 32
- `juniorguru-cas`: "Jak se naučit programovat?", oddíl "Kolik času potřebuješ", junior.guru, https://web.archive.org/web/20220127090955/https://junior.guru/learn/ ; autor Honza Javorek (junior.guru je jeho autorský projekt); snímek archivu - Network accessline 32
- `juniorguru-cas`: "Jak se naučit programovat?", oddíl "Kolik času potřebuješ", junior.guru, https://web.archive.org/web/20220127090955/https://junior.guru/learn/ ; autor Honza Javorek (junior.guru je jeho autorský projekt); snímek archivu - Network accessline 33
- `lupa-bankid`: "Bankovní identita je dobrý sluha. Existují ale i důvody, proč ji nechtít", Lupa.cz, https://www.lupa.cz/clanky/bankovni-identita-je-dobry-sluha-existuji-ale-i-duvody-proc-ji-nechtit/ ; autor Kamil Zmeškal; 19. 1. 2021; důk - Network accessline 33
- `lupa-bankid`: "Bankovní identita je dobrý sluha. Existují ale i důvody, proč ji nechtít", Lupa.cz, https://www.lupa.cz/clanky/bankovni-identita-je-dobry-sluha-existuji-ale-i-duvody-proc-ji-nechtit/ ; autor Kamil Zmeškal; 19. 1. 2021; důk - Network accessline 34
- `jirovsky-vysledek`: "Krizový web s vysokou dostupností za pár hodin", blog Česko.Digital, https://blog.cesko.digital/2020/03/web-mzcr ; autor Václav Jirovský; 20. 3. 2020 (text původně vyšel na serveru Náš WordPress); důkaz: datovaný člá - Network accessline 34
- `jirovsky-vysledek`: "Krizový web s vysokou dostupností za pár hodin", blog Česko.Digital, https://blog.cesko.digital/2020/03/web-mzcr ; autor Václav Jirovský; 20. 3. 2020 (text původně vyšel na serveru Náš WordPress); důkaz: datovaný člá - Network accessline 35
- `jirovsky-tipy`: "Krizový web s vysokou dostupností za pár hodin", oddíl "Obecné tipy pro podobný web", blog Česko.Digital, https://blog.cesko.digital/2020/03/web-mzcr ; autor Václav Jirovský; 20. 3. 2020; důkaz: datovaný článek a jmenova - Network accessline 35
- `jirovsky-tipy`: "Krizový web s vysokou dostupností za pár hodin", oddíl "Obecné tipy pro podobný web", blog Česko.Digital, https://blog.cesko.digital/2020/03/web-mzcr ; autor Václav Jirovský; 20. 3. 2020; důkaz: datovaný článek a jmenova - Network accessline 36
- `praha-obcan-role`: "Portál Pražana – Zkušenosti se zaváděním (Lessons learned)", slide 5, konference ISSS 2021, https://archiv.isss.cz/archiv/2021/download/prezentace/praha_petr.pdf ; autor Ing. Jan Petr, MHMP; 20. 9. 2021; důkaz: datova - Network accessline 36
- `praha-obcan-role`: "Portál Pražana – Zkušenosti se zaváděním (Lessons learned)", slide 5, konference ISSS 2021, https://archiv.isss.cz/archiv/2021/download/prezentace/praha_petr.pdf ; autor Ing. Jan Petr, MHMP; 20. 9. 2021; důkaz: datova - Network accessline 37
- `praha-investice`: "Portál Pražana – Zkušenosti se zaváděním (Lessons learned)", slide 11, konference ISSS 2021, https://archiv.isss.cz/archiv/2021/download/prezentace/praha_petr.pdf ; autor Ing. Jan Petr, MHMP; 20. 9. 2021; důkaz: datova - Network accessline 37
- `praha-investice`: "Portál Pražana – Zkušenosti se zaváděním (Lessons learned)", slide 11, konference ISSS 2021, https://archiv.isss.cz/archiv/2021/download/prezentace/praha_petr.pdf ; autor Ing. Jan Petr, MHMP; 20. 9. 2021; důkaz: datova - Network accessline 41
The skill adapts [unslop](https://github.com/backnotprop/pstack/blob/main/skills/unslop/SKILL.md), [wait-what](https://github.com/mattpocock/skills/blob/main/skills/productivity/wait-what/SKILL.md), and Wikipedia's [Signs of AI writing](htt - Network accessline 41
The skill adapts [unslop](https://github.com/backnotprop/pstack/blob/main/skills/unslop/SKILL.md), [wait-what](https://github.com/mattpocock/skills/blob/main/skills/productivity/wait-what/SKILL.md), and Wikipedia's [Signs of AI writing](htt
skills/writing/references/cs-pairs.md
- Network accessline 12
> nebude možné nahrávat změny. Přesný termín ukončení odstávka zatím není > znám. > Více na: http://wiki.openstreetmap.org/wiki/2016_May_server_maintenance - Network accessline 12
> nebude možné nahrávat změny. Přesný termín ukončení odstávka zatím není > znám. > Více na: http://wiki.openstreetmap.org/wiki/2016_May_server_maintenance - Network accessline 13
> znám. > Více na: http://wiki.openstreetmap.org/wiki/2016_May_server_maintenance > Ostatní služby, jako hlavní stránka, wiki i dlaždice běží normálně. - Network accessline 13
> znám. > Více na: http://wiki.openstreetmap.org/wiki/2016_May_server_maintenance > Ostatní služby, jako hlavní stránka, wiki i dlaždice běží normálně. - Network accessline 14
> Více na: http://wiki.openstreetmap.org/wiki/2016_May_server_maintenance - Network accessline 14
> Více na: http://wiki.openstreetmap.org/wiki/2016_May_server_maintenance - Network accessline 84
> restaurace nám otevřou až ve čtvrtek a stejně platí omezení na max 4 lidi u > stolu, zveme vás s Tomem na online Kvartální pivo, které proběhne zítra, > 2.12. od 18:00 na https://meet.fit.vutbr.cz/sotm - Network accessline 84
> restaurace nám otevřou až ve čtvrtek a stejně platí omezení na max 4 lidi u > stolu, zveme vás s Tomem na online Kvartální pivo, které proběhne zítra, > 2.12. od 18:00 na https://meet.fit.vutbr.cz/sotm - Network accessline 85
> stolu, zveme vás s Tomem na online Kvartální pivo, které proběhne zítra, > 2.12. od 18:00 na https://meet.fit.vutbr.cz/sotm > Je to stejná konference, na které se bude následně konat i letošní SOTM. - Network accessline 85
> stolu, zveme vás s Tomem na online Kvartální pivo, které proběhne zítra, > 2.12. od 18:00 na https://meet.fit.vutbr.cz/sotm > Je to stejná konference, na které se bude následně konat i letošní SOTM. - Network accessline 86
> 2.12. od 18:00 na https://meet.fit.vutbr.cz/sotm - Network accessline 86
> 2.12. od 18:00 na https://meet.fit.vutbr.cz/sotm
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 60 facts
- Network access in prose of documentationskills/git-workflow/references/conventional-commits.md:14Low confidence
- Network access in prose of documentationgit-workflow/references/conventional-commits.md:14Low confidence
- Network access in prose of documentationskills/git-workflow/references/pr.md:73Low confidence
- Network access in prose of documentationgit-workflow/references/pr.md:73Low confidence
- Network access in prose of documentationskills/writing/references/README.md:17Low confidence
- Network access in prose of documentationwriting/references/README.md:17Low confidence
- Network access in prose of documentationskills/writing/references/README.md:18Low confidence
- Network access in prose of documentationwriting/references/README.md:18Low confidence
- Network access in prose of documentationskills/writing/references/README.md:19Low confidence
- Network access in prose of documentationwriting/references/README.md:19Low confidence
- Network access in prose of documentationskills/writing/references/README.md:20Low confidence
- Network access in prose of documentationwriting/references/README.md:20Low confidence
- Network access in prose of documentationskills/writing/references/README.md:21Low confidence
- Network access in prose of documentationwriting/references/README.md:21Low confidence
- Network access in prose of documentationskills/writing/references/README.md:22Low confidence
- Network access in prose of documentationwriting/references/README.md:22Low confidence
- Network access in prose of documentationskills/writing/references/README.md:23Low confidence
- Network access in prose of documentationwriting/references/README.md:23Low confidence
- Network access in prose of documentationskills/writing/references/README.md:24Low confidence
- Network access in prose of documentationwriting/references/README.md:24Low confidence
- Network access in prose of documentationskills/writing/references/README.md:25Low confidence
- Network access in prose of documentationwriting/references/README.md:25Low confidence
- Network access in prose of documentationskills/writing/references/README.md:26Low confidence
- Network access in prose of documentationwriting/references/README.md:26Low confidence
- Network access in prose of documentationskills/writing/references/README.md:27Low confidence
- Network access in prose of documentationwriting/references/README.md:27Low confidence
- Network access in prose of documentationskills/writing/references/README.md:28Low confidence
- Network access in prose of documentationwriting/references/README.md:28Low confidence
- Network access in prose of documentationskills/writing/references/README.md:29Low confidence
- Network access in prose of documentationwriting/references/README.md:29Low confidence
- Network access in prose of documentationskills/writing/references/README.md:30Low confidence
- Network access in prose of documentationwriting/references/README.md:30Low confidence
- Network access in prose of documentationskills/writing/references/README.md:31Low confidence
- Network access in prose of documentationwriting/references/README.md:31Low confidence
- Network access in prose of documentationskills/writing/references/README.md:32Low confidence
- Network access in prose of documentationwriting/references/README.md:32Low confidence
- Network access in prose of documentationskills/writing/references/README.md:33Low confidence
- Network access in prose of documentationwriting/references/README.md:33Low confidence
- Network access in prose of documentationskills/writing/references/README.md:34Low confidence
- Network access in prose of documentationwriting/references/README.md:34Low confidence
- Network access in prose of documentationskills/writing/references/README.md:35Low confidence
- Network access in prose of documentationwriting/references/README.md:35Low confidence
- Network access in prose of documentationskills/writing/references/README.md:36Low confidence
- Network access in prose of documentationwriting/references/README.md:36Low confidence
- Network access in prose of documentationskills/writing/references/README.md:37Low confidence
- Network access in prose of documentationwriting/references/README.md:37Low confidence
- Network access in prose of documentationskills/writing/references/README.md:41Low confidence
- Network access in prose of documentationwriting/references/README.md:41Low confidence
- Network access in prose of documentationskills/writing/references/cs-pairs.md:12Low confidence
- Network access in prose of documentationwriting/references/cs-pairs.md:12Low confidence
and 10 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/audit/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/audit/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/audit/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/audit/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/audit/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
