Not in the top 1,000 by GitHub stars
adjustleads/provenskills-free-packs
Free agent skill packs (SKILL.md) from ProvenSkills: meetings, plain writing, retention, claims desk, skill authoring. CC BY-NC 4.0.
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
claims-field-kit/carrier-letter/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
claims-field-kit/deadline-research/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
claims-field-kit/first-notice-checklist/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
claims-field-kit/inspection-narrative/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
claims-field-kit/settlement-counter/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
meeting-ops/decision-log/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
meeting-ops/follow-up-email/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
meeting-ops/meeting-prep-brief/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
meeting-ops/weekly-priorities/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
plain-writing/announcement/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
plain-writing/customer-email/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
plain-writing/cut-it-in-half/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
plain-writing/say-it-plainly/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
retention-desk/dunning-email/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
retention-desk/exit-interview/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
retention-desk/save-play/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
skill-author-kit/pack-readme/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
skill-author-kit/release-notes/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
skill-author-kit/trigger-check/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
skill-author-kit/write-a-skill/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f857a2446b3b
No earlier version was observed for comparison.
Heat
0.4- 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
- Carrier letter
claims-field-kit/carrier-letter - Deadline research
claims-field-kit/deadline-research - First notice checklist
claims-field-kit/first-notice-checklist - Inspection narrative
claims-field-kit/inspection-narrative - Settlement counter
claims-field-kit/settlement-counter - Decision log entry
meeting-ops/decision-log - Follow-up email
meeting-ops/follow-up-email - Meeting prep brief
meeting-ops/meeting-prep-brief - Weekly priorities
meeting-ops/weekly-priorities - Announcement
plain-writing/announcement - Customer email
plain-writing/customer-email - Cut it in half
plain-writing/cut-it-in-half - Say it plainly
plain-writing/say-it-plainly - Dunning email
retention-desk/dunning-email - Exit interview
retention-desk/exit-interview - Save play
retention-desk/save-play - Pack README
skill-author-kit/pack-readme - Release notes
skill-author-kit/release-notes - Trigger check
skill-author-kit/trigger-check - Write a skill
skill-author-kit/write-a-skill
How it works
Carrier letter
When your agent uses it
Use when you need a proof-of-loss cover letter or a supplement request to a carrier. Drafts from the policy language and figures you paste, under your license.
What it loads into context
Frontmatter
170 tokensAlways available to the agent
SKILL.md
1,597 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
- Step 0, Who is signing
- Step 1, Collect what the letter needs
- Step 2, Draft
- Step 3, Hand it back
- Rules
- Important
Files
SKILL.mdcore7,273 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubDeadline research
When your agent uses it
Use when someone asks what clock applies to a claim in a state. Researches current statute and policy conditions, cites each source, lists deadlines to confirm.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
1,239 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
- Step 1, Get the facts
- Step 2, Research the state
- Step 3, Read the policy
- Step 4, List the candidate deadlines
- Rules
- Important
Files
SKILL.mdcore5,669 bytesSKILL.mdcore5,669 bytesSKILL.mdcore5,669 bytesSKILL.mdcore5,669 bytesSKILL.mdcore5,669 bytesSKILL.mdcore5,669 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubFirst notice checklist
When your agent uses it
Use when a new loss call or email comes in and you want to capture everything before it is lost. Intake checklist, questions in order, paste-ready summary.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
1,182 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
- Step 1, Read what you were given
- Step 2, Ask in this order
- Step 3, Hand back the summary block
- Rules
- Important
Files
SKILL.mdcore5,023 bytesSKILL.mdcore5,023 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubInspection narrative
When your agent uses it
Use when you are back from a site visit and want field notes and a photo list turned into a dated inspection note. Room by room, with what is still missing.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
1,003 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
- Step 1, Collect the inputs
- Step 2, Organize by area
- Step 3, Write the photo captions
- Step 4, Produce the note
- Rules
- Important
Files
SKILL.mdcore4,452 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSettlement counter
When your agent uses it
Use when a carrier estimate comes back and you want to know what to challenge. Reads the pasted estimate, lists items to question, drafts the counter to review.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
1,355 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
- Step 1, Get the inputs
- Step 2, Read the estimate for gaps
- Step 3, Draft the counter
- Step 4, Hand it back
- Rules
- Important
Files
SKILL.mdcore6,173 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubDecision log entry
When your agent uses it
Use when someone pastes meeting notes, a transcript, or a thread and asks what was decided. Extracts every decision, owner, and deadline into a log entry the team can hold each other to.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
345 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
- Output format
- Rules
Files
SKILL.mdcore1,484 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubFollow-up email
When your agent uses it
Use when a meeting just ended and someone asks for the follow-up, recap, or next-steps email. Writes a short email that confirms decisions and assigns actions without corporate filler.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
369 tokensWhen the skill is activated
Reference documents
163 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Structure
- Rules
Files
SKILL.mdcore1,616 bytesreferences/email-checklist.mddoc708 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubMeeting prep brief
When your agent uses it
Use when someone shares an upcoming meeting, an agenda, or a calendar invite and wants to walk in prepared. Produces a one-page brief with the goal, the questions to ask, and the risks to watch.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
505 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
- What to collect first
- Company context
- The brief
- Rules
Files
SKILL.mdcore2,238 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubWeekly priorities
When your agent uses it
Use when someone dumps their task list, inbox, or worries and asks what to work on this week. Turns the pile into a ranked plan with a reason for every cut.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
454 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
- The measuring stick
- Process
- Rules
Files
SKILL.mdcore1,949 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubAnnouncement
When your agent uses it
Use when someone must tell customers about a release, feature, policy change, or price change and asks for the announcement, release note, or email.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
711 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
- Collect first
- Structure
- Rules
- Output
Files
SKILL.mdcore3,047 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubCustomer email
When your agent uses it
Use when a customer or client wrote in and someone asks for a reply, a response, or what to say back. Answers first, in the owner's voice, no canned closers.
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
739 tokensWhen the skill is activated
Reference documents
263 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How the owner talks
- Before you write
- Structure
- Rules
- Output
Files
SKILL.mdcore3,251 bytesreferences/reply-checklist.mddoc1,120 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubCut it in half
When your agent uses it
Use when a draft runs long and someone asks to cut, shorten, tighten, or trim it, or get it down to half. Halves the length and keeps every fact.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
725 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
- Procedure
- Output
- Rules
Files
SKILL.mdcore3,058 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSay it plainly
When your agent uses it
Use when a draft sounds like an AI wrote it, or someone asks to make it less AI, more human, plain English, or like them. Rewrites it, facts unchanged.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
1,175 tokensWhen the skill is activated
Reference documents
832 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Procedure
- Output
- Punctuation
- Framing
- Vocabulary
- Structure
- Rhythm
- Substance
- When a writing sample is provided
- Do not over-flag
Files
SKILL.mdcore5,170 bytesSKILL.mdcore5,170 bytesreferences/ai-vocabulary.mddoc3,744 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubDunning email
When your agent uses it
Use when a payment failed or an invoice is past due and you want a personal note, not the processor's robot. Three short emails, subject lines, a reply plan.
What it loads into context
Frontmatter
145 tokensAlways available to the agent
SKILL.md
811 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
- Before drafting
- The sequence
- If they reply
- Rules
Files
SKILL.mdcore3,523 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubExit interview
When your agent uses it
Use when a customer just canceled and you want to learn why without a survey. One-question email, the reply if they answer, and a line for your reasons list.
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
656 tokensWhen the skill is activated
Reference documents
565 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Before drafting
- The email
- If they answer
- Log the reason
- Rules
Files
SKILL.mdcore2,877 bytesreferences/cancel-reasons.mddoc2,358 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSave play
When your agent uses it
Use when a customer is about to cancel, went quiet, or asked to downgrade, and you need to decide what to say. Says why they are churning and drafts the note.
What it loads into context
Frontmatter
166 tokensAlways available to the agent
SKILL.md
952 tokensWhen the skill is activated
Reference documents
824 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What to collect
- Step 1. Name the signal
- Step 2. Pick one tactic
- Step 3. Draft the note
- Output
- Rules
Files
SKILL.mdcore4,028 bytesreferences/churn-signals.mddoc3,730 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubPack README
When your agent uses it
Use when a pack is ready to list and someone asks for the README, store page, or buyer summary. Writes who it's for, one line per skill, and what buyers need.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
695 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
- What to collect first
- The README
- Rules
Files
SKILL.mdcore2,955 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubRelease notes
When your agent uses it
Use when a new pack version ships and someone pastes a diff or a list of changes and asks for release notes. Writes what changed for the buyer, nothing more.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
574 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
- What to collect first
- Step 1, sort the changes
- Step 2, write the notes
- Rules
Files
SKILL.mdcore2,479 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubTrigger check
When your agent uses it
Use when a skill won't fire, or someone asks if a description matches what buyers type. Tests eight buyer phrasings and rewrites the description till they hit.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
767 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
- What to collect first
- Step 1, write eight phrasings
- Step 2, score the current description
- Step 3, rewrite
- Step 4, hand it over
- Rules
Files
SKILL.mdcore3,442 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubWrite a skill
When your agent uses it
Use when someone wants to turn a process into a skill, or asks how to write a SKILL.md. Asks five questions, then writes the full file with frontmatter.
What it loads into context
Frontmatter
98 tokensAlways available to the agent
SKILL.md
1,135 tokensWhen the skill is activated
Reference documents
1,687 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 1, get the process
- Step 2, write the frontmatter
- Step 3, write the body
- Step 4, check it
- Step 5, hand it over
- Rules
Files
SKILL.mdcore4,983 bytesreferences/example-skill.mddoc2,016 bytesreferences/spec.mddoc5,364 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- Carrier letter
- Deadline research
- First notice checklist
- Inspection narrative
- Settlement counter
- Decision log entry
- Follow-up email
- Meeting prep brief
- Weekly priorities
- Announcement
- Customer email
- Cut it in half
- Say it plainly
- Dunning email
- Exit interview
- Save play
- Pack README
- Release notes
- Trigger check
- Write a skill
Repository facts
- License
- No license detected
- Created
- Sep 7, 2026
- Last pushed
- Sep 7, 2026
- Forks
- 0
- Open issues
- 0
- Project activity
- Active
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 7 notes
claims-field-kit/deadline-research/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaims-field-kit/deadline-research/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaims-field-kit/deadline-research/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaims-field-kit/deadline-research/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaims-field-kit/deadline-research/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaims-field-kit/first-notice-checklist/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplain-writing/say-it-plainly/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- No network access
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- 1 reference to secretsin 1 file: write-a-skill/references/spec.md:43
- No requests to vote in Hot
Show the signal with its line
skill-author-kit/write-a-skill/references/spec.md
- Access to secretsline 43
[Credential-related source omitted]
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: 1 fact
- Access to secrets in prose of documentationwrite-a-skill/references/spec.md:43Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Unknown | No evidence | |
| Codex | Unknown | No evidence | |
| Cursor | Unknown | No evidence | |
| Gemini CLI | Unknown | No evidence | |
| GitHub Copilot | Unknown | No evidence | |
| OpenCode | Unknown | No evidence |
- 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.
