Micro
Skill2 starsChanged 5 months agoApache-2.0View on GitHub
Write all micro specs for one group — fully self-contained implementation units, plus the group's simulation scenarios and human-testing checklist.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- dandavison/agent-skillstheir own version, first seen Oct 17, 2026
- openai/pluginstheir own version, first seen Oct 13, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- openai/plugins★ 7.8ksame name
- dandavison/agent-skills★ 3same name
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 repository22 other files it gives its agents.
- A1 — Design & Master-Spec ConsistencySkill
- A2 — Spec ReviewSkill
- A3 — PolishSkill
- A4 — North Star DirectionSkill
- A5 — Web AuditSkill
- AcceptSkill
- AmendSkill
- BrainstormSkill
- ClarifySkill
- ClosureSkill
- ConstituteSkill
- DesignSkill
- DiscoverSkill
- FeatureSkill
- Final — The F-PassSkill
- HelpSkill
- ImplementSkill
- InitSkill
- North StarSkill
- ResumeSkill
- SpecifySkill
- StatusSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
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 23
Read Section 13; extract the group's specs (IDs, titles, dependencies, sizes).
- Distinctive: line 31
Coverage verification: every FR and AC assigned to the group is covered by at least one spec.
- Distinctive: line 46
Brownfield: add a per-spec Scope Boundary section and an inherited vs introduced column in File Operations.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Micro — Write One Group's Specs
Write all micro specs for one group in a single invocation. Each micro spec is a fully self-contained implementation unit — readable without the master spec — carrying its own objective, the full text of the FRs/ACs it covers, a File Operations table, acceptance criteria, and implementation notes.
Gate: the northstar phase must be accepted, AND the group must have a brainstorm entry (/genesis-brainstorm --boundary micro for G{N}).
Inputs
.genesis/project-state.md(mode)spec.md(required — for the Section 13 plan),northstar.md(required),design.md,brainstorm-log.mdapprovals/master.json(verify northstar accepted)- The constitution; any existing specs in
micro-specs/
Process
- Parse the group number
G{N}(refuse if missing). - Read Section 13; extract the group's specs (IDs, titles, dependencies, sizes). Cycle-detect the within-group dependency graph; refuse on a cycle. Verify the group exists in the plan.
- Create
.genesis/features/<feature>/micro-specs/. - Write specs sequentially in topological dependency order — write one, validate, save, commit, then the next. No batching, no parallel authoring. For each spec, from
micro-spec-template.md:- Frontmatter: title, spec-id, group, feature, status, dependencies, covers (FR/AC), deferred, reads, writes.
- Objective; Requirements Covered (full FR/AC text, not just IDs); Dependencies table; content sections; Acceptance Criteria; File Operations (create/modify/delete, mode-aware); Implementation Notes; commit message + PR description.
- Self-contained check: an implementer must be able to build from this spec alone — all FRs/ACs in full text, paths specific, ACs objectively verifiable.
- Size check: >500 lines → warn and auto-split into
{G.S.1}/{G.S.2}if reasonable (update the plan); else note and proceed. - Validate the frontmatter schema, stamp
last_validated, then commit.
- Coverage verification: every FR and AC assigned to the group is covered by at least one spec; report any uncovered.
- Produce group simulation scenarios (mandatory) covering functional flows, UI/UX states, integration points, stress scenarios, regression risks.
- Produce a human testing checklist for hands-on testing after merge.
- Final commit for plan updates + simulations + checklist.
Output
.genesis/features/<feature>/micro-specs/{Group.Spec}.md— one self-contained spec per file (e.g.1.3.md)..genesis/features/<feature>/simulations/g{N}-scenarios.md— group simulation scenarios. Feeds the F-pass Simulation stage..genesis/features/<feature>/reviews/g{N}-human-review.md— human testing checklist.- Possibly updated
spec.md(Section 13) if a spec was auto-split.
Mode differences
- Greenfield: technical implementation specs (code files, APIs, components).
- Brownfield: add a per-spec Scope Boundary section and an inherited vs introduced column in File Operations; ACs add "no regressions."
- Lowfield: process-stage specs (command templates, artifact schemas, pipeline behavior); ACs verify the stage command exists, the artifact schema validates, and pipeline behavior is correct.
Next step
Implement each spec in order with /genesis-implement, then run the audits.
Natural language triggers
- "write micro specs for group 1"
- "decompose group 0"
- "micro G2"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.

