skill-author

Guidance for deciding whether a recurring development practice deserves its own reusable skill and for creating that skill when it does. A skill is a set of instructions an AI coding agent loads for a particular kind of work.

In plain words
What is it for?
Use it when creating, reviewing, or improving a project-specific skill, especially after the same expert correction or workflow has come up repeatedly.
Why use it?
It prevents one-off advice and mechanically checkable rules from becoming unnecessary skills. This keeps the skill library focused on methods that genuinely require repeated judgment.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/tradebaas/groundwork/skill-author
Any agent
npx skills add Tradebaas/Groundwork --skill skill-author
Clone the repo
git clone --depth 1 https://github.com/Tradebaas/Groundwork

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 764 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00052 $0.00764
Opus 5 $0.00026 $0.00382
Sonnet 5 $0.00010 $0.00153
Haiku 4.5 $0.00005 $0.00076

Measured 2d ago against content hash f01f00c2a380, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-author scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/skill-author/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skill-author: grow the library deliberately, or not at all

The studied failure mode is real: a library of 557 imported skills with 3 in use. Skills are context spent on every session's listing. Each one must earn that. The general rule this ladder instances - every addition declares where it is paid, and the always-on surface carries the highest bar - is decision 0015.

1. Should this be a skill? (ladder: stop at the first rung)

  1. One-off knowledge? Put it in the task, not the library.
  2. A durable fact or rule? It belongs in the owning doc (docs/standards/, DESIGN.md, AGENTS.md if truly universal), not a skill.
  3. Mechanically checkable? Add a check to checks/check.mjs + a fixture test. Never send a model to do a linter's job.
  4. Recurring method requiring judgment (a way of working you'd teach a new senior hire) → that is a skill. The trigger: you've needed it three times, or you know you will.

2. Write it

Create .agents/skills/<name>/SKILL.md (open Agent Skills standard):

  • Frontmatter: name = directory name (lowercase, hyphens, ≤64 chars); description ≤1024 chars stating what it does and when to load it. Write the trigger phrases the moment of need actually contains; this line is all the model sees when deciding to load it.
  • Body ≤500 lines, imperative, information-dense. Structure: purpose (one line) → the method (numbered, decision points explicit; ladders beat essays) → what to record → how it relates to the automated gates (judgment layer above, never duplicate of).
  • Heavy reference material goes in files next to SKILL.md, linked one level deep, loaded only when needed. No code snippets that will go stale: point at the living source instead.
  • End the body's report instruction with the ⚓ convention if the skill produces user output.

3. Register and validate

  • Add one row to the skills table in AGENTS.md (keep the ≤150-line budget: if it doesn't fit, something else must leave; that trade-off is the point).
  • Run node checks/check.mjs. It validates frontmatter, name/dir match, and budgets.
  • Test the trigger: describe the situation to a fresh session and confirm the skill loads.

Read the full file on GitHub · 53 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 53 lines · 52 tokens per session scan A f01f00c2a380

Subscribe to this mod's changes

skill-author is a skill published in the GitHub repository Tradebaas/Groundwork (2 stars, last pushed 7d ago), licensed MIT. It adds 52 tokens to every session and 764 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

mission-driver

Create roadmaps and mission configs, then drive the mission-driver AI dev-loop engine. mission-driver lives at tools/mission-driver/ — it reads missions/ .json and loops CHECK → REVIEWPLANS → EXECPLANS → DRAFTPLANS → DEEPAUDIT until the roadmap is done or the audit budget is exhausted. Use this skill when the user…

entropy-cloud/attractor-guided-engineering-template · 199 tokens

keel-plan

Create or revise PLAN.md — propose the phase DAG (phases · gates · dependencies) from the user's goal, get approval, write the table and regenerate the colored Mermaid diagram from it. Statuses flip at rituals (/keel-handover, /keel-phase-review); post-completion fixes land in the Fix log.

muratsilahtaroglu/claude-code-starter-kit · 70 tokens

keel-stats

Render the ritual telemetry visually — turns .claude/ritual-log into reports/ritual-stats.md with PLAN.md-style colored Mermaid interval boxes (session/compact boundaries) + a counts table. Answers "which skills/commands/hooks ran, how often, in which interval".

muratsilahtaroglu/claude-code-starter-kit · 62 tokens

sdd-serve

Serve the SDD Builder's AI request queue: claim requests with sddnextrequest, draft the proposal, answer with sddrespondrequest. Never writes spec files — the user accepts each proposal in the builder. Use when the user asks to attend, serve or listen to the SDD board queue. / Atiende la cola de peticiones del SDD…

juanklagos/spec-driven-development-template · 80 tokens

init

Configure an uninitialized project from an approved charter: stack, scripts, identity, optional Git, and verification.

bnet47/codexicon · 24 tokens

sdd-workflow

Guide a project with Spec-Driven Development (SDD) discipline - idea, approved spec, consistent plan, tasks, a gate that verifies approval and consent, implementation, validation, and logbook. Bilingual EN/ES. Use when the user wants to start, spec, plan, implement, or validate work with SDD, or mentions specs, plans…

juanklagos/spec-driven-development-template · 84 tokens