CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

75

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

87%Weight 40%Scale 1-3

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

The body is lean, highly actionable, and well-organized with executable commands and valuable gotchas. Its main weakness is workflow_clarity: the core destructive symlink/commit workflow lacks explicit validation checkpoints.

Suggestions

Add a verification step after symlinking (e.g., `ls -l ~/.pi/agent/skills/<skill-name>` and confirm the symlink target resolves) before committing, since the doc itself flags symlink writes as destructive.

Insert a validation checkpoint confirming the directory name matches the frontmatter `name` field before commit, turning the stated mismatch gotcha into an explicit workflow step.

Add a quick post-commit sanity check (e.g., verify the new skill loads or appears in the skill list) to close the feedback loop on the destructive/batch operations in the main process.

DimensionReasoningScore

Conciseness

Lean and assumes competence — minimal preamble, executable commands, and non-obvious gotchas (the `-g`/`-y` picker hang) that earn their tokens rather than padding; not a 2 because there is little to tighten without losing useful procedural detail.

3 / 3

Actionability

Provides copy-paste-ready commands (mkdir, ln -sf, git add/commit, npx -y skills add ... -g -y) and concrete templates/directory structures, fully executable rather than descriptive.

3 / 3

Workflow Clarity

The 6-step sequence is clear, but the main symlink/commit workflow lacks explicit validation checkpoints despite involving destructive operations (the doc itself warns cat > symlink destroys the target); verification appears only in the external-packs section, so this is capped at 2.

2 / 3

Progressive Disclosure

Self-contained SKILL.md with no bundle files present and no nested references; content is well-organized into coherent sections with clear navigation and nothing that needs splitting out for a process skill.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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

The description is specific, well-triggered, and complete, naming concrete actions and a focused niche with explicit natural-language triggers. It cleanly satisfies all four dimensions.

DimensionReasoningScore

Specificity

Names a concrete action ("Create new joelclaw skills") plus several distinct process attributes ("repo-canonical, symlinked, git-tracked, slogged"), matching the multiple-specific-actions anchor; not a 2 because coverage is comprehensive rather than partial.

3 / 3

Completeness

Explicitly answers what ("Create new joelclaw skills with the idiomatic process...") and when via an explicit trigger clause ("Triggers on 'add a skill'..."), satisfying the Use-when requirement that would otherwise cap at 2.

3 / 3

Trigger Term Quality

Includes natural phrases a user would actually say — "add a skill", "create skill", "new skill", "canonical skill", "make a skill for" — giving good coverage of likely request terms.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (authoring joelclaw skills) with distinct, specific trigger phrases unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
joelhooks/joelclaw
Reviewed

Table of Contents

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.