skill-development
Skill7 starsChanged 8 days agoMITView on GitHub
Use for creating, editing, reviewing, auditing, or maintaining project-authored skills, including their assets, descriptions, invocation modes, references, scripts, and adjacent contract tests. Also use for discovery, installation reach, optional peers, promotion, public skill catalogs and READMEs, script contract architecture, skill categories, and standalone behavior.
22 other projects use a version of this.
Adopted by
Most recently taken up by
- rooftop-Owl/skill-factorytheir own version, first seen Nov 8, 2026
- shkodnik1917/claude-brainlabtheir own version, first seen Nov 8, 2026
- Vepricov/claude-brainlabtheir own version, first seen Nov 1, 2026
- halkn/skillstheir own version, first seen Oct 25, 2026
- bosens-China/tc39-atlastheir own version, first seen Oct 23, 2026
- davidanthonyn/claude-skillstheir own version, first seen Oct 20, 2026
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- anthropics/claude-plugins-official★ 46ksame name
- Galaxy-Dawn/claude-scholar★ 5.9ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- luocfprime/labtasker★ 39same name
- shkodnik1917/claude-brainlab★ 35same name
- Vepricov/claude-brainlab★ 35same name
- jorgeasaurus/agent-skills★ 14same name
- tstapler/dotfiles★ 8same name
12 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- auditSkill
- harmonizeSkill
- shell-integrationSkill
- agent-task-directoriesSkill
- agent-task-relaySkill
- agent-documentationSkill
- browser-automationSkill
- cli-subagentSkill
- full-reviewSkill
- prepushSkill
- vitest-conventionsSkill
- dom-release-notes-for-humansSkill
- dom-sensible-commit-flowSkill
- dom-sensible-contribution-flowSkill
- fish-shell-scriptingSkill
- human-facing-writingSkill
- intentional-dependency-choiceSkill
- posix-shell-scriptingSkill
- refine-agent-workflowSkill
- release-notes-for-humansSkill
- sensible-commit-flowSkill
- sensible-contribution-flowSkill
- simple-github-cliSkill
- subagent-review-flowSkill
- verify-findingsSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 21 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 28
Documentation: When authoring, reviewing, auditing, or maintaining skill documentation, follow Skill Authoring for entrypoints, references, …
- Distinctive: line 29
Descriptions: When authoring or assessing a skill’s description or invocation mode, follow Skill Descriptions.
- Distinctive: line 31
Public catalogs: When maintaining a public skill catalog or its collection README, follow Maintain Public Skill Catalogs.
“Common” is measured: kept by at least 6 in 10 of the 21 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill Development
Resolve Skill Scope
Resolve each in-scope skill through Skill Installation before planning, including during reviews and audits. Apply the consuming project’s instructions rather than assuming that source location determines installation reach.
For documentation work, including assets, catalogs, metadata, public READMEs, and references, compose with agent-documentation. It owns the shared lifecycle for authority, ownership, writing composition, changes, reviews, validation, and reporting. Add the contracts selected below without restarting that lifecycle. For script-only work without documentation changes, follow the script route directly.
An explicit change takes precedence when the request also uses review or audit language. Standalone reviews and audits remain read-only. Apply the global Explicit user direction policy to this skill’s authoring conventions and procedures, including routed contracts. A procedural waiver doesn’t change a script’s implemented capabilities or bypass native access controls. Select every applicable contract before starting the work it governs, and load each once.
Select Contracts
- Documentation: When authoring, reviewing, auditing, or maintaining skill documentation, follow Skill Authoring for entrypoints, references, overlays, examples, and inherited policy.
- Descriptions: When authoring or assessing a skill’s description or invocation mode, follow Skill Descriptions.
- Public behavior: For every public skill or canonical public-surface asset in scope, follow Public Skill Portability. Also follow it for every public mirror or standalone default affected by a global instruction change or evaluation, even when the request names only the global source. Select its conditional creation, promotion, naming, and optional peer contracts before the corresponding work. Its README contract applies when creating or updating a public skill README.
- Public catalogs: When maintaining a public skill catalog or its collection README, follow Maintain Public Skill Catalogs.
- Script contracts: Before planning a new or changed skill-owned script, adjacent contract test, or script-owned artifact, or reviewing or auditing one, follow Skill-Owned Scripts. This skill owns necessity, canonical ownership and location, observable interfaces, operation modes, effects, artifacts, schemas, invocation, and contract coverage. The owning domain skill supplies domain semantics, and applicable implementation workflows govern internal concerns.
Keep Skill Contents Operational
Never document auxiliary information anywhere in a project-authored skill directory. Auxiliary information records how the skill itself was authored or maintained without helping a reader understand or execute its advertised workflow. Examples include change histories, research logs, review records, and verification baselines. Keep durable context in the source project’s reference documentation and task-local evidence in the conversation or task artifacts outside the skill. Preserve operational requirements, safety boundaries, and supporting explanations needed to apply the skill.
Validate Selected Contracts
For documentation work, use agent-documentation’s Select Validation Scope to determine applicable checks. Run identity checks for skill creation or changes to names or discovery. Run installation and link checks for creation or changes to installation mappings, paths, or links. Apply those checks when their contracts are under review or audit, and select other checks from the affected contracts. Validate complete declared scopes, including affected mirror families and the full description set when required. Conditional loading doesn’t limit an invariant to changed lines or excuse skipping validation of an unchanged declaration covered by the active contract.
For documentation work, return the skill-specific results to agent-documentation’s shared validation and reporting lifecycle. For script-only work, complete the script contract’s validation and report concrete contract findings or the resulting change and any limitations under the applicable communication policy. Don’t turn a contract review into an implementation audit.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

