#737 by GitHub stars
kharmanskyi/open-steps
Plain-language agent skills for Claude Code, Codex, Cursor and Gemini CLI: honest session reports, straight verdicts, steps you can follow. MIT.
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/os-ask-simple/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4fa744ba8ea0 → 4fa744ba8ea0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4fa744ba8ea0
No earlier version was observed for comparison.
skills/os-big-picture/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4fa744ba8ea0 → 4fa744ba8ea0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4fa744ba8ea0
No earlier version was observed for comparison.
skills/os-check-work/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4fa744ba8ea0 → 4fa744ba8ea0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4fa744ba8ea0
No earlier version was observed for comparison.
skills/os-done-or-not/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4fa744ba8ea0 → 4fa744ba8ea0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4fa744ba8ea0
No earlier version was observed for comparison.
skills/os-say-simple/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4fa744ba8ea0 → 4fa744ba8ea0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4fa744ba8ea0
No earlier version was observed for comparison.
skills/os-step-by-step/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4fa744ba8ea0 → 4fa744ba8ea0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4fa744ba8ea0
No earlier version was observed for comparison.
skills/os-what-could-go-wrong/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4fa744ba8ea0 → 4fa744ba8ea0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4fa744ba8ea0
No earlier version was observed for comparison.
skills/os-whats-next/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4fa744ba8ea0 → 4fa744ba8ea0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4fa744ba8ea0
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit 4fa744ba8ea06ccf128a39853824c46ac391dd00
git clone --filter=blob:none --no-checkout https://github.com/kharmanskyi/open-steps.git .hotskills/kharmanskyi-open-steps && git -C .hotskills/kharmanskyi-open-steps checkout --detach 4fa744ba8ea06ccf128a39853824c46ac391dd00
# Copy each selected skill directory from .hotskills/kharmanskyi-open-steps into .claude/skills/<skill-name>/1.3kGitHub stars
-12stars in 7 days
8skills in this repository
0commits in 30 days
Heat
0.1- Star growth, last 7 daysAhead of 1% of tracked repositories
- Star growth, last 24 hoursAhead of 3% of tracked repositories
- Rank movement, last 7 daysAhead of 2% of tracked repositories
- Commits, last 30 daysAhead of 0% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- os-ask-simple
skills/os-ask-simple - os-big-picture
skills/os-big-picture - os-check-work
skills/os-check-work - os-done-or-not
skills/os-done-or-not - os-say-simple
skills/os-say-simple - os-step-by-step
skills/os-step-by-step - os-what-could-go-wrong
skills/os-what-could-go-wrong - os-whats-next
skills/os-whats-next
How it works
os-ask-simple
When your agent uses it
ALWAYS invoke this skill before asking the user any technical question or offering options, and whenever they ask to be asked in plain words - "ask simple", "ask me simply", "ask me in plain words" - in any language. ALWAYS invoke it too when the user asks for your view on a technical choice: whether it is worth doing, more than the problem needs, or replaceable by something simpler, and which option you would take. Invoke it even when the code makes the answer look obvious: the checks are what make the answer more than a guess. Rewrites the question in plain words and always ends with one marked recommendation. A structural choice first passes six checks, shown as a table: effort now, simpler substitute, extra work later, lock-in, over-engineering, easy to undo. Doing nothing is always weighed.
What it loads into context
Frontmatter
214 tokensAlways available to the agent
SKILL.md
1,271 tokensWhen the skill is activated
Reference documents
675 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Language
- When to use
- Before anything: is this even a question for them?
- Light form - every question
- Full form - six checks, for structural choices
- Hard rules
- Known gotchas
Files
../../.claude-plugin/marketplace.jsonasset545 bytes../../.claude-plugin/plugin.jsonasset587 bytes../../hooks/hooks.jsonasset582 bytesSKILL.mdcore5,435 bytesreferences/01-sign-in-now-or-later.mddoc2,903 bytes
Read SKILL.md
# os-ask-simple
Two jobs. Ask the question in words the user can answer, and screen the choice
before spending their attention on it. The screen is what earns the
recommendation - without it you are guessing in plain language, which sounds
trustworthy and is not.
## Language
Write in the language the user speaks in this session. Detect it from the
conversation. Keep code, file names and identifiers in English.
## When to use
os-big-picture
When your agent uses it
ALWAYS invoke this skill when the user asks where the project as a whole stands - "where are we", "what's the big picture", "what have we built", "what is in this project", "map the project", "what does this thing even do", "what is stale", "what can we delete", "update the roadmap" - in any language, and whenever a session report has just been written. It keeps one file, BIG-PICTURE.md: what the product is, every feature with how far it got, which parts nobody has touched, and what is queued next. Age and wiring are measured from git; how far a feature got comes from the reports or says "not checked". Where a tracker is connected it offers to open the queue as tickets, after a yes and never before. Never invents work, never deletes code.
What it loads into context
Frontmatter
300 tokensAlways available to the agent
SKILL.md
2,049 tokensWhen the skill is activated
Reference documents
2,571 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 1 - find the file, and never clobber it
- Step 2 - the census, measured by the script
- Step 3 - reading what it printed
- Step 4 - the backlog, sourced and never invented
- Step 5 - the tracker, if there is one
- Step 6 - plain words, before it is written
- The shape
- Hard rules - these rules *are* the skill
Scripts executed separately
scripts/census.sh
Files
SKILL.mdcore7,616 bytesSKILL.mdcore7,616 bytesSKILL.mdcore7,616 bytesSKILL.mdcore7,616 bytesSKILL.mdcore7,616 bytesSKILL.mdcore7,616 bytesreferences/01-quiet-is-not-dead.mddoc3,756 bytesreferences/rationale.mddoc6,611 bytesscripts/census.shruns4,024 bytes
Read SKILL.md
# os-big-picture
One file, `BIG-PICTURE.md`, where `os-whats-next` already looks for a backlog.
It answers "where are we now" - not a plan, nothing in it a promise. Write it
in the user's language; paths stay English.
**When to use it.** The user asks where the project stands, or there is no
`BIG-PICTURE.md` yet → the full pass: describe, census, signals, backlog. A
session report was just written → the fold-in: only the rows that session
touched. Both re-measure, because a session that moves no row is the one after
which the dates go quietly stale.
## Step 1 - find the file, and never clobber it
os-check-work
When your agent uses it
ALWAYS invoke this skill when the user asks about work done outside this session - "check work", "check the others", "check other sessions" - or to accept one: "the session is done, check it", "can we merge it" - in any language. You are the receiving party: treat the report as a claim, verify each part against machine state, name every gap between claimed and true. Verified-ready work merges in the same pass. End with what is left, one next step, and any reply another session needs, ready to paste.
What it loads into context
Frontmatter
226 tokensAlways available to the agent
SKILL.md
1,861 tokensWhen the skill is activated
Reference documents
592 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Language
- The stance
- Two modes
- Sweep
- Accept - steps 1 to 5 (never per-session inside a sweep)
- The reply is part of the pass
- Ending the pass
- Hard rules
- Known gotchas
Files
SKILL.mdcore7,580 bytesreferences/01-accepting-a-build-session.mddoc2,367 bytes
Read SKILL.md
# os-check-work
You are the receiving party: another session says it finished, and your job
is to find out whether that is true. Reports run optimistic - they are written
by whoever did the work. Triggers live in the description above; one more is
taking over work you did not do.
## Language
Write in the language the user speaks in this session, detected from the
conversation. Code, file names and identifiers stay English.
## The stance
os-done-or-not
When your agent uses it
ALWAYS invoke this skill when work wraps up or the user asks how it went - "done or not", "are we done", "what happened", "report", "what's the status of this ticket" - in any language, and when a Stop hook asks for a session report. Produces a ten-line plain- language report: a lead, a checkmark table, and a verdict - fully done, anything needed from you, new debt, safe to close. Every "yes" names its proof; unverified says "not checked". Saves the report so the next session starts from it instead of re-exploring the repo.
What it loads into context
Frontmatter
213 tokensAlways available to the agent
SKILL.md
1,902 tokensWhen the skill is activated
Reference documents
951 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Language
- Step 1 - gather proof that takes seconds
- Step 2 - name the outcome
- Step 3 - write the report (translate the labels, keep the shape)
- Step 4 - save it
- Step 5 - fold it into the map
- Jargon → plain words
- Hard rules - these rules *are* the skill
- Known gotchas
Files
SKILL.mdcore7,270 bytesSKILL.mdcore7,270 bytesreferences/01-prod-promote.mddoc3,700 bytes
Read SKILL.md
# os-done-or-not
One question, one screen: **did the agent finish, and what actually happened**,
in words a reader who does not code will understand. Nothing happened (pure
questions, no files touched) → one line saying so, no report.
## Language
The user's language in this session, detected from the conversation. Translate
every template label. Code, files, commands stay English.
## Step 1 - gather proof that takes seconds
Fast checks only; never re-run the test suite - use results this sessionos-say-simple
When your agent uses it
ALWAYS invoke this skill when the user asks for simpler or shorter about something said or written - "say it simply", "what does this mean", "I don't understand your answer", "too long", "wait, what?", "bro" - in any language, about any text: your own answer, a report, a review comment, an error. "I don't understand what to DO" is os-step-by-step; this skill restates text. It restates for a reader who does not read code: leads with the point, keeps every number, warning and caveat - no facts added, no bad news dropped. A number returns exactly that many points, most important first.
What it loads into context
Frontmatter
182 tokensAlways available to the agent
SKILL.md
1,273 tokensWhen the skill is activated
Reference documents
424 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Language
- When to use
- What text to restate
- The controlled-language rules
- With a number
- Hard rules
- Known gotchas
Files
SKILL.mdcore5,206 bytesSKILL.mdcore5,206 bytesSKILL.mdcore5,206 bytesSKILL.mdcore5,206 bytesreferences/01-wall-of-text.mddoc1,779 bytes
Read SKILL.md
# os-say-simple
A text exists and the user cannot use it. This skill rewrites it into words
they can act on - the pack's rescue skill: the others fire at moments of work,
this one whenever any text, including your own, needs saying again properly.
It changes only the words. Never the facts.
## Language
Write in the language the user speaks in this session. Detect it from the
conversation. Keep code, file names and identifiers in English.
## When to use
os-step-by-step
When your agent uses it
ALWAYS invoke this skill when you need the user to act - run a command, paste a secret, click, approve - and whenever they ask how to do something or say they do not know what to do: "step by step", "walk me through it", "what do I do", "what should I do", "I don't understand what to do", "explain what I need to do", in any language. Picking which task comes next is os-whats-next; this skill is for doing the thing in front of you. First earn the ask: try it yourself, find another route, shrink it to the part only they can do. Then one action per step, commands labelled by what they touch, no jargon. Commands are single lines that prompt for any value - typing hidden for secrets - and confirm in plain words. Afterwards verify their step.
What it loads into context
Frontmatter
218 tokensAlways available to the agent
SKILL.md
1,920 tokensWhen the skill is activated
Reference documents
1,043 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Language
- When to use
- Step 0 - earn the right to ask
- The shape
- After they act - verify, do not trust
- Secrets and dangerous steps
- Choices, not instructions
- Hard rules
- Known gotchas
Files
SKILL.mdcore7,539 bytesSKILL.mdcore7,539 bytesSKILL.mdcore7,539 bytesSKILL.mdcore7,539 bytesreferences/01-paste-a-secret.mddoc4,088 bytes
Read SKILL.md
# os-step-by-step
The user is not stuck because the task is hard - they cannot tell what they
are being asked to do. This skill turns "I need something from you" into an
instruction a person who does not read code can follow without a follow-up
question. `os-done-or-not` reports *that* something is needed; this one says
exactly *how*.
## Language
Write in the language the user speaks in this session, detected from the
conversation. Commands, file names and identifiers stay English.
## When to useos-what-could-go-wrong
When your agent uses it
ALWAYS invoke this skill before anything hard to undo gets agreed to - a contract, a purchase, a migration, a launch, a price change, a reorganisation - and whenever the user asks "what could go wrong", "what are we missing", "poke holes in this", or for a premortem or a red team, in any language. Assumes the decision already failed and works backwards to find out why, in a fresh agent that had no hand in making it. Sweeps nine areas and shows what each produced, including the empty ones. Ends on one verdict: go ahead, go but fix these first, try it small first, think again, do not do this.
What it loads into context
Frontmatter
206 tokensAlways available to the agent
SKILL.md
1,801 tokensWhen the skill is activated
Reference documents
11,927 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Language
- Step 1 - write down what is actually being decided
- Step 2 - hand it to an agent that had no part in it
- Step 3 - give it to the user straight
- Hard rules
- Known gotchas
- The analysis prompt, verbatim
Scripts executed separately
scripts/prompt.sh
Files
SKILL.mdcore7,357 bytesSKILL.mdcore7,357 bytesSKILL.mdcore7,357 bytesreferences/01-office-lease.mddoc14,668 bytesreferences/02-clinic-database-move.mddoc21,995 bytesreferences/premortem-prompt.mddoc10,614 bytesreferences/why-these-rules.mddoc1,293 bytesscripts/prompt.shruns472 bytes
Read SKILL.md
# os-what-could-go-wrong
Assume it already failed, then work backwards to find out why - while there is
still time to change it. The attack runs in a fresh agent that had no part in
the decision, because an agent that helped shape one reviews it far too
gently: it defends its own reasoning, and it misses the thing that kills the
plan out of politeness.
`os-ask-simple` screens a choice before the user picks one. This one runs
after the choice is made and before it can no longer be taken back.
## Language
Write in the language the user speaks in this session, detected from theos-whats-next
When your agent uses it
ALWAYS invoke this skill when the user asks what to do next, what is left, or what is blocked - "what's next", "what now", "what should we work on", "anything I can do" - in any language. This skill picks the next piece of work; when the user asks HOW to do a thing or says they do not understand what to do, that is os-step-by-step. Reads the last report, local changes, open pull requests and always the backlog. First finishes what is finished: verified-ready pull requests merge in the same pass. Then sorts the rest into doable-alone and needs-you, ending with one recommended next task in plain words - what it closes or unblocks. Never invents tasks.
What it loads into context
Frontmatter
264 tokensAlways available to the agent
SKILL.md
1,890 tokensWhen the skill is activated
Reference documents
597 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Language
- When to use
- Step 1 - read the state, quickest first
- Step 2 - finish what is finished
- Step 3 - sort what remains into two lists
- The shape - ten lines, like every report in this pack
- How many at once
- Hard rules
- Known gotchas
Scripts executed separately
../os-big-picture/scripts/census.sh
Files
../os-big-picture/scripts/census.shruns4,024 bytesSKILL.mdcore7,609 bytesSKILL.mdcore7,609 bytesSKILL.mdcore7,609 bytesreferences/01-end-of-day.mddoc2,549 bytes
Read SKILL.md
# os-whats-next
Answer "what do we do now" with the next move, not a map. The user does not
need the dependency graph - they need what got finished, what to take next,
and why, in plain words. This skill decides; `os-step-by-step` walks the user
through their part; `os-done-or-not` reports what came of it.
## Language
Write in the language the user speaks in this session, detected from the
conversation. Commands, file names and identifiers stay English.
## When to use
Skills included
- os-ask-simple
- os-big-picture
- os-check-work
- os-done-or-not
- os-say-simple
- os-step-by-step
- os-what-could-go-wrong
- os-whats-next
Repository facts
- License
- MIT
- Created
- Aug 25, 2026
- Last pushed
- Oct 5, 2026
- Forks
- 111
- Open issues
- 5
- Project activity
- Active
Rank over the last 12 weeks
Now #737 · best #640 · down 13 in 30 days
- #718 on Nov 1
- #720 on Nov 2
- #724 on Nov 3
- #729 on Nov 4
- #733 on Nov 5
- #737 since Nov 6
61 earlier periods
- #924 on Aug 23
- #936 on Aug 25
- #920 on Aug 26
- #923 on Aug 27
- #958 on Aug 28
- #873 on Aug 29
- #876 on Aug 30
- #924 on Aug 31
- #958 on Sep 1
- #923 on Sep 2
- #928 on Sep 3
- #890 on Sep 4
- #865 on Sep 5
- #901 on Sep 6
- #925 on Sep 7
- #938 on Sep 8
- #922 on Sep 9
- #917 on Sep 10
- #879 on Sep 11
- #878 from Sep 12 to Sep 13
- #915 on Sep 14
- #902 on Sep 15
- #907 on Sep 16
- #899 on Sep 17
- #875 on Sep 18
- #835 on Sep 19
- #829 on Sep 20
- #826 on Sep 21
- #842 on Sep 22
- #816 on Sep 23
- #784 on Sep 24
- #748 on Sep 25
- #746 on Sep 26
- #761 on Sep 27
- #781 on Sep 28
- #792 on Sep 29
- #772 on Sep 30
- #710 on Oct 1
- #711 on Oct 2
- #682 on Oct 3
- #714 on Oct 5
- #719 on Oct 6
- #724 on Oct 7
- #748 on Oct 8
- #716 on Oct 9
- #700 on Oct 10
- #699 on Oct 11
- #715 on Oct 12
- #720 on Oct 13
- #719 on Oct 14
- #692 on Oct 15
- #677 on Oct 18
- #723 on Oct 20
- #728 on Oct 21
- #682 on Oct 23
- #640 on Oct 24
- #726 on Oct 25
- #717 on Oct 28
- #720 on Oct 29
- #711 on Oct 30
- #716 on Oct 31
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 3, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 16 notes
skills/os-big-picture/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/os-big-picture/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/os-big-picture/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/os-big-picture/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/os-big-picture/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/os-done-or-not/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/os-say-simple/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/os-say-simple/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/os-say-simple/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/os-step-by-step/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/os-step-by-step/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/os-step-by-step/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/os-what-could-go-wrong/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/os-what-could-go-wrong/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/os-whats-next/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/os-whats-next/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- 2 broad permissionsin 2 files: os-big-picture/SKILL.md:1 os-what-could-go-wrong/SKILL.md:1
- No dangerous shell commands
- 10 network referencesin 2 files: .claude-plugin/plugin.json:14 .claude-plugin/marketplace.json:10
- No hidden or obfuscated text
- No instruction overrides
- 3 executable scriptsin 2 files: os-big-picture/scripts/census.sh:1 os-what-could-go-wrong/scripts/prompt.sh:1
- No access to secrets
- No requests to vote in Hot
Show all 15 signals by file
.claude-plugin/marketplace.json
- Network accessline 10
"source": "./", "description": "Plain-language skills for coding agents, for the person running development who does not read code: session reports, decisions, next steps and the whole picture.", "homepage": "https://opensteps.a - Network accessline 11
"description": "Plain-language skills for coding agents, for the person running development who does not read code: session reports, decisions, next steps and the whole picture.", "homepage": "https://opensteps.ai", "repository" - Network accessline 12
"homepage": "https://opensteps.ai", - Network accessline 13
"repository": "https://github.com/kharmanskyi/open-steps"
.claude-plugin/plugin.json
- Network accessline 14
"author": { "name": "Pavlo Kharmanskyi", "url": "https://github.com/kharmanskyi" - Network accessline 15
"name": "Pavlo Kharmanskyi", "url": "https://github.com/kharmanskyi" }, - Network accessline 16
"url": "https://github.com/kharmanskyi" - Network accessline 17
}, "homepage": "https://opensteps.ai", "repository": "https://github.com/kharmanskyi/open-steps" - Network accessline 18
"homepage": "https://opensteps.ai", - Network accessline 19
"repository": "https://github.com/kharmanskyi/open-steps"
skills/os-big-picture/SKILL.md
- Broad permissionsline 1
Bash(bash ${CLAUDE_SKILL_DIR}/scripts/census.sh *)
skills/os-big-picture/scripts/census.sh
skills/os-what-could-go-wrong/SKILL.md
- Broad permissionsline 1
Bash(bash ${CLAUDE_SKILL_DIR}/scripts/prompt.sh)
skills/os-what-could-go-wrong/scripts/prompt.sh
- Executable scriptline 1
#!/usr/bin/env bash
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.
No combined signals at this commit.
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/os-ask-simple/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/os-ask-simple/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/os-ask-simple/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/os-ask-simple/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/os-ask-simple/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.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/kharmanskyi-open-steps/)