add-skill

Create new joelclaw skills with the idiomatic process — repo-canonical, symlinked, git-tracked, slogged. Triggers on 'add a skill', 'create skill', 'new skill', 'canonical skill', 'make a skill for', or any request to formalize a process or domain into a reusable skill.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/add-skill/SKILL.md

Quality

Content

68%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An extremely token-efficient body that encodes real policy and safety boundaries without padding. Its weakness is execution: the multi-step authoring process is expressed as abstract prose rather than an explicit sequence, and the concrete steps are delegated to an external workflow without saying where they can be found.

Suggestions

Rewrite the four prose paragraphs as an explicit numbered workflow (resolve ownership → draft frontmatter and procedure → test → install → verify → commit) with the verification steps as explicit checkpoints, e.g. '4. Verify: confirm consumers resolve to the intended source before committing.'

Add one concrete artifact example — a minimal valid frontmatter block or the directory layout of an installed skill — so 'write concise frontmatter, the domain-specific procedure, its real boundaries' has an executable referent.

Add short section headers (Ownership, Authoring, Testing, Installation) so the four phases are scannable, and state where the referenced `write-a-skill` workflow's full procedure lives so the delegation is actionable.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense with zero padding ('Use the installed `write-a-skill` workflow to create or revise a skill. Resolve source ownership first...'), explaining nothing Claude already knows. Every sentence carries a rule or boundary, matching the 'every token earns its place' anchor.	5 / 5
Actionability	There is some concrete guidance — a named workflow to invoke, an explicit ownership mapping ('standing fleet policy belongs to dark-wizard, runtime services to joelclaw'), and specific prohibitions — but the actual authoring procedure is left as high-level direction ('Write concise frontmatter, the domain-specific procedure, its real boundaries') with no concrete steps, commands, or examples. This sits between minimal guidance and executable guidance.	3 / 5
Workflow Clarity	The paragraphs imply a rough sequence (resolve ownership → infer outcome → write → test → install → commit) and include some verification language ('Inspect installed links before changing them', 'verify that consumers resolve to the intended source'), but the sequence is never made explicit and checkpoints remain implicit within prose, matching 'sequence present but checkpoints missing or implicit' rather than the clearly sequenced anchor 4.	3 / 5
Progressive Disclosure	The skill is under 50 lines with no bundle files and a single clearly signaled one-level pointer (the installed `write-a-skill` workflow), so no content needs splitting. It falls short of the top anchor only because the body has no section organization — four unheaded prose paragraphs under one H1.	4 / 5
	Total	15 / 20 Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with explicit, natural trigger phrases and a clear what/when structure. The only weakness is that the capability side rests on a single action plus jargon-laden attribute adjectives rather than an enumeration of what the process actually does.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Create new joelclaw skills') and one concrete action, with attribute adjectives ('repo-canonical, symlinked, git-tracked, slogged') that describe the result rather than additional actions. It does not list several distinct concrete actions, so it matches 'names domain and 1-2 concrete actions, but not comprehensive' rather than the level-4 anchor.	3 / 5
Completeness	It explicitly answers both what ('Create new joelclaw skills with the idiomatic process') and when ('Triggers on ... or any request to formalize a process or domain into a reusable skill') with concrete trigger phrases, matching the top anchor. The 'when' clause is fully explicit rather than weakly implied, so it is not a 4.	5 / 5
Trigger Term Quality	Five natural quoted phrases ('add a skill', 'create skill', 'new skill', 'canonical skill', 'make a skill for') are exactly what a user would say, plus a semantic catch-all. A few natural variants (e.g., 'write a skill', 'build a skill') are missing, keeping it below the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche (authoring joelclaw skills specifically) with distinct, skill-creation-specific trigger phrases; overlap risk with generic workflow skills is minimal.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: joelhooks/joelclaw
Path: skills/add-skill/SKILL.md
Commit: aa0116c

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.