build-skill
Skill0 starsChanged 4 months agoMITView on GitHub
Create a single skill file following one of 5 proven archetypes. Use when adding a workflow to a team, creating a new skill, building a process for a task, defining an automation, or writing agent instructions.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- yigitkonur/skills-by-yigitkonurtheir own version, first seen Nov 1, 2026
- Revxrsal/aranjiyyahtheir own version, first seen Oct 20, 2026
- lowkey-divine/sovereign-skillstheir own version, first seen Oct 11, 2026
- agent0ai/agent-zerotheir own version, first seen Oct 8, 2026
- LukeRenton/explore-claude-codetheir own version, first seen Jul 23, 2026
- kjanat/skillstheir own version, first seen Jun 30, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- agent0ai/agent-zero★ 20ksame name
- LukeRenton/explore-claude-code★ 329same name
- roerohan/skills★ 29same name
- yigitkonur/skills-by-yigitkonur★ 13same name
- shawn-dumas/claude-code-skills★ 1same name
- kjanat/skills★ 0same name
- lowkey-divine/sovereign-skills★ 0same name
- Revxrsal/aranjiyyah★ 0same 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 repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- audit-teamSkill
- build-agentSkill
- build-pipelineSkill
- build-teamSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Read research/skill-design-mastery.md for the full archetype analysis, 8 design rules, anti-patterns, sizing guide, and composition …
- Very specific: line 14
Read standards/skill-authoring.md — the authoring rules every generated skill must pass: trigger-bearing frontmatter description, 200-line …
- Distinctive: line 44
Order instructions: MUST-level rules at top, reference material in middle, task prompt at end.
- Distinctive: line 52
Mandatory pre-reads: before any work.
- Distinctive: line 61
Run these checks on the generated skill:
- Distinctive: line 75
If any check fails, fix before delivering.
“Common” is measured: kept by at least 6 in 10 of the 8 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
Build Skill
Trigger
"Create a skill", "build a workflow for", "add a [X] skill", "I need a process for [X]", "write instructions for [task]".
Research (Read Before Building)
- Read
research/skill-design-mastery.mdfor the full archetype analysis, 8 design rules, anti-patterns, sizing guide, and composition patterns. - Read
standards/skill-authoring.md— the authoring rules every generated skill must pass: trigger-bearing frontmatter description, 200-line cap with extract-to-reference, no hardcoded absolute paths (workspace-relative only), referenced tools must exist, self-edit changelog convention.
Key findings to apply:
- Critical instructions first, task at end. Primacy bias: earlier instructions get 2.3-2.6x better compliance (IFScale, 2025). Lost-in-the-middle: 30%+ drop at mid-positions (Liu et al., TACL 2024).
- Under 50-100 core instructions. Top models hit 68% accuracy at 500 instructions. Stay in the high-reliability zone.
- One skill, one job. Multi-tool agents fail non-deterministically (arXiv:2512.08769). Single-responsibility skills composed as pipelines are more reliable.
- Binary gates, not advisory. "Consider checking" produces optional behavior. "If not: BLOCKED" produces blocking behavior.
The 5 Archetypes
| Archetype | When | Lines | Template |
| TASK | One agent does the whole thing | 80-200 | templates/skill-task.md |
| PIPELINE | Multiple stages, each depends on prior | 150-300 | templates/skill-pipeline.md |
| PARALLEL-SPAWN | Specialists work independently then combine | 80-150 | templates/skill-parallel-spawn.md |
| COMMAND | Manages a team and makes decisions | 80-120 | templates/skill-command.md |
| ACTIVATION | Boots up a division | 50-80 | templates/skill-activation.md |
Generate Process
- Ask: What does this skill do? Which archetype fits?
- Select template from
templates/. - Fill domain-specific content:
- Role declaration with authority tier (ADVISORY/COMMIT/BLOCK/VETO/HALT — Floor Spec ladder)
- 3+ mandatory pre-reads with file paths
- Numbered process steps in imperative voice
- Binary gates (PASS/BLOCK) with specific thresholds
- Explicit output format with save location
- Add 5+ trigger phrases to the description. Claude undertriggers by default.
- Order instructions: MUST-level rules at top, reference material in middle, task prompt at end.
- Add circuit breaker: Max retries, max round-trips, timeout conditions.
- Add learnings section (empty, for production hardening).
Skill Design Rules (8 Rules from 72-Skill Analysis)
- Under 200 lines. Reasoning degrades at ~3,000 tokens (Goldberg et al., 2024). 200 lines of markdown is ~2,000-3,000 tokens. Extract reference tables to companion files.
- Binary gates (PASS/BLOCK), not advisory ratings.
- Mandatory pre-reads before any work.
- Explicit output format with save location.
- Versioned learnings from real failures, with dates.
- Pushy trigger description. List 5-8 natural-language trigger phrases.
- Authority declaration up front (one ladder tier: ADVISORY/COMMIT/BLOCK/VETO/HALT).
- Circuit breaker. Max retries, max round-trips, timeout.
Validate After Building
Run these checks on the generated skill:
- Description has 5+ trigger phrases
- Pre-reads list specific file paths that exist (or will exist)
- Process has numbered steps in imperative voice
- Every gate is binary (PASS/BLOCK), not advisory
- Output format specifies exact file path pattern
- Total line count under 200 (or under 300 for pipeline skills)
- Critical instructions appear in the first 20 lines
- Circuit breaker defined (max retries or round-trips)
- Authority tier declared (ADVISORY/COMMIT/BLOCK/VETO/HALT)
- No placeholder text ("TBD", "TODO", "[fill in]")
- No hardcoded absolute paths; every referenced tool/script/agent exists (
standards/skill-authoring.md)
If any check fails, fix before delivering.
Parallel Fan-Out Note
For any multi-item batch (N ≥ 2 posts, audits, reviews, analyses, cleanups), spawn one top-level agent per item, running in parallel, rather than routing the batch through a single orchestrator that processes items serially or via internal sub-agents invisible to the user.
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.

