tap-skill-authoring — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited tap-skill-authoring (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A skill is a reusable instruction pack at skills/<name>/SKILL.md. When it activates — preloaded, auto-activated by its rules, or loaded with skill(action="use") or /skill <name> — its body is injected into the session's context. Skills don't define a role, model, or tools; they add focused knowledge any agent in their domain can use.
A skill is a checklist for a model that already knows the field. Anthropic's skill guidance starts from "Claude is already very smart — only add context Claude doesn't already have." Every token ships on every activation, so the body carries decisions, conventions, and gates, not textbook background. Activation is decided by the frontmatter (domains plus rules), so the frontmatter is as much a part of the design as the body.
skills/<skill-name>/
├── SKILL.md # required
├── reference/ # long reference files, cited from the body and lint-checked
├── scripts/ # executables the skill tells the agent to run
├── assets/ # templates and resources
└── validate # optional output validator (chmod +x)On activation the runtime lists every file under scripts/, references/, and assets/ with absolute paths in a Skill Resources section. reference/ (singular, the tap convention) is not in that list, so cite those files from the body by path; lint-skills.sh fails if a cited reference/<file> does not exist. Keep references one level deep from SKILL.md.
---
name: skill-name
title: "Skill Title"
description: "What this skill does and when to use it."
license: Apache-2.0
compatibility: "Requires: tool1. macOS/Linux."
capabilities: versioning
domains: developer
rules:
- file(Cargo.toml)
- content(rust) content(async)
---| Field | Required | Rules |
|---|---|---|
name | yes | ≤64 chars, lowercase letters, digits, hyphens; no leading/trailing hyphen; equals the directory name |
title | yes (tap lint) | 5–60 chars |
description | yes | 20–1024 chars, third person, what it does plus when to use it with concrete trigger terms |
domains | for auto-activation | Space-separated or array; each value must be an existing agents/<domain>/ directory (lint); the runtime also accepts * for every domain, but tap lint rejects it |
rules | for auto-activation | List of rule expressions, below |
capabilities | optional | Capabilities enabled when the skill activates; each must exist under capabilities/ (lint) |
compatibility | optional | ≤500 chars, environment only (tools, OS, network) |
license, metadata, allowed-tools | optional | allowed-tools is space-separated; missing tools are reported as an incompatibility |
The runtime parser reads name, description, compatibility, license, allowed-tools, capabilities, domains, and rules; a skill without name or description is skipped. Without both domains and rules, a skill is manual-only.
Rules are evaluated on fresh user messages when [skills] auto_activation is on and the session domain is in domains. Each - item is an OR branch; several expressions on one line are ANDed.
| Expression | Matches when |
|---|---|
file(<path or glob>) | Path exists in the workdir, or the glob matches (*.rs, src/**/*.go) |
content(<word>) | User message contains the word (whole word, case-insensitive) |
match(<regex>) | User message matches the regex (nested parentheses are fine) |
grep(<pattern>[, <glob>]) | A gitignore-respecting workdir file contains the pattern; the glob filters by file name only (*.toml, not src/**/*.rs) |
env(<VAR>) / env(<VAR>=<value>) | Variable set and non-empty / equals value |
bin(<command>) | Command found on PATH |
workdir(<text>) | Working-directory path contains the text (case-insensitive) |
session(<text>) | Session name contains the text (case-insensitive). Default names are YYMMDD-<dir>-HHMM-<id>; tap run sessions are tap-<domain>-<spec>-<hex>, so session(<spec>) targets one agent only in tap runs or -n-named sessions |
semantic(<phrase>[, <threshold>]) | Embedding cosine between the message and the phrase clears the threshold (default 0.65) |
Deterministic matches activate directly. Semantic-only candidates must also beat the runner-up by a 0.06 margin, so near-ties abstain. Adding or changing semantic(...) phrases changes the tap embedding model's training data — see the tap-model-training skill.
skills/<name>/validate runs at the end of each assistant turn while the skill is active, only when [skills] auto_validation = true (default false), and only for skills that come from a tap. Contract: argv[1] is assistant, the final assistant message arrives on stdin, cwd is the project workdir. A non-zero exit with non-empty stderr counts as a failure and the stderr is fed back to the model; retries per skill are capped by [skills] max_retries, timeout by validation_timeout. Make it executable.
Fixed section order, U-shaped for attention: the opening and the closing get read most carefully, the middle relies on headers as anchors.
## Overview why and when (2–4 sentences)
## Mental model governing principles
## Rules tables, bullets, decision guides
## Examples bad → good pairs
## Checklist verifiable gates before shipping
## Composition / References sibling skills in the same domain, sourcesreference/.lint-skills.sh warns above 3000 body words and fails above 4500; Anthropic recommends keeping SKILL.md under 500 lines.reference/*.md; SKILL.md stays the navigator.# H1 at the top of the body (frontmatter title is the title), no bold, no italics, no --- rules inside the body — all lint failures. Tables and code fences stay.The same calibration as agent prompts: current Claude models follow instructions precisely and over-trigger on emphatic language.
CRITICAL: YOU MUST X → X.NEVER/ALWAYS bullets → plain Don't … / Do …MANDATORY: headers → descriptive section namesReserve all-caps for one or two genuine safety hard-stops. Full guidance: skills/prompt-engineering/reference/claude-4-emphasis-and-tools.md.
domains: single-valued wherever possible — pick the domain that owns the deliverable.compatibility: describes the environment, never pairings with agents.rust-error-handling, not rust).templates/skill.md; write frontmatter, then the body in canonical order.domains + rules only if it should auto-activate; test that the rules match the intended prompts and nothing broader.validate.bash scripts/lint-skills.sh skills/<name>; test with /skill <name> in a session.---
name: git-workflow
title: "Git Workflow"
description: "Commit message conventions and branch naming. Use when committing or creating branches."
license: Apache-2.0
---
## Overview
Encodes Conventional Commits and branch naming.
## Rules
- Prefix commits with `feat:`, `fix:`, `chore:`.
- Branch names: `feat/short-description`, `fix/short-description`.---
name: programming-rust
title: "Rust Programming"
description: "Rust idioms, error handling, async patterns. Auto-activates in Rust projects."
domains: developer
rules:
- file(Cargo.toml)
- grep(tokio, Cargo.toml) content(async)
- semantic(write idiomatic rust code)
---❌ # Git Workflow as the first body line — lint fails with BODY_HAS_REDUNDANT_H1.
❌ grep(async_trait, src/**/*.rs) — the glob is matched against file names only, so it never matches. Use grep(async_trait, *.rs).
❌ domains: dev — no agents/dev/ directory, so lint fails and it would never activate.
name equals the directory; domains and capabilities reference real directories?---; under ~2000 words?reference/ files exist; validate executable if present?bash scripts/lint-skills.sh skills/<name> passes?templates/skill.md — canonical skill templatetap-model-training — retrain after changing semantic(...) phrases~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.