agent-skills-archive-orchestrator
Skill1 starsChanged 6 months agoMITView on GitHub
Use when creating, revising, reviewing, or validating deployable skills in this repository while keeping project harness artifacts separate from the skill archive.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- call-r-lib-in-pythonSkill
- code-commenterSkill
- code-reviewerSkill
- end-user-xp-improverSkill
- fp-developerSkill
- lesson-documenterSkill
- plan-designerSkill
- preferred-workflowSkill
- release-preparerSkill
- scientific-prose-editorSkill
- simple-code-writerSkill
- spec-driven-developerSkill
- wayback-link-fallbackSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Use this skill for repository tasks that create, modify, review, validate, or document skills under skills/, or that change the deploy …
- Very specific: line 13
Do not use this skill for ordinary downstream use of an installed skill.
- Very specific: line 33
keep large optional detail in references/ or examples/
- Distinctive: line 45
Test or validation output, including any command that could not be run.
- Distinctive: line 51
If a task asks to install skills into this repo as a project target, call out that the target path may overlap with the repo-local harness …
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Agent Skills Archive Orchestrator
When to Use
Use this skill for repository tasks that create, modify, review, validate, or document
skills under skills/, or that change the deploy tooling used to install those skills.
Do not use this skill for ordinary downstream use of an installed skill. Do not treat
files under .agents/skills/ as archive content.
Required Inputs
- The user request and intended target skill, if any.
- Current contents of the affected
skills/<skill-name>/directory. - Any deploy-tooling files touched by the request, especially
src/agent_skills_archive/deploy.pyandtests/. - Existing repo guidance from
AGENTS.mdanddocs/harness/agent-skills-archive/team-spec.md.
Workflow
- Classify the task as one or more of: new skill, skill revision, skill review, deploy-tooling change, documentation update, or harness update.
- Confirm the target surface:
- deployable archive content belongs under
skills/ - repo-local agent workflow belongs under
.agents/,docs/harness/, or_workspace/
- deployable archive content belongs under
- Inspect existing files before editing. Preserve unrelated user changes.
- For archive skills, keep
SKILL.mddiscoverable:- include YAML frontmatter with
nameanddescription - match
nameto the skill directory - keep large optional detail in
references/orexamples/
- include YAML frontmatter with
- Record intermediate handoffs in
_workspace/when the task has multiple phases or review evidence worth preserving. - Validate with the narrowest useful checks:
uv run deploy-skills --list-skillsuv run deploy-skills --dry-run --skill <skill-name>for affected skillsuv run python -m unittest discover -s testswhen deploy code or metadata behavior changed
- Summarize changed surfaces and validation results.
Expected Outputs
- Updated archive skill files, deploy code, docs, or harness files as requested.
- A short note distinguishing archive changes from project-harness changes.
- Test or validation output, including any command that could not be run.
Validation Notes
- The deploy command discovers only the archive source at
skills/by default. - Project harness skills under
.agents/skills/should have normal skill frontmatter for agent usability, but they are not part of the archive. - If a task asks to install skills into this repo as a project target, call out that the target path may overlap with the repo-local harness and confirm the intended destination before copying.
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.

