CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-authoring

Create, port, revise, or audit repo-local skills and their metadata, engineering contracts, and task routes. Use for skill discovery, ownership, source grounding, and session-derived guidance; diagrams are optional.

58

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/skill-authoring/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

A well-structured instruction-only skill with a sequenced workflow, completion criteria, acceptance scenarios, and condition-scoped one-level-deep references that all exist in the bundle. Its main weaknesses are redundancy across the routing sections and validation checkpoints that are named but not executable.

Suggestions

Consolidate the routing rules stated three times ('Build a routed skill hierarchy', 'Workflow' steps 2/6/7, and 'Completion criteria') into one authoritative section, keeping the workflow as pure sequence, to cut noticeable repetition.

Merge or sharply delimit 'Keep skills current after code changes' and 'Derive revisions from a working session', which cover overlapping update-trigger and classification guidance.

Make validation executable by stating the actual validator command (and the fix-and-rerun loop) instead of 'Run the default skill validator', and consider moving the detailed contract-authoring bullet lists into an existing reference to slim the body.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but routing rules are restated across 'Build a routed skill hierarchy', 'Workflow' steps 2/6/7, 'Route skills by task', and 'Completion criteria', and 'Keep skills current after code changes' substantially overlaps 'Derive revisions from a working session', leaving noticeable tightening opportunities.

3 / 5

Actionability

Concrete, copy-paste-ready guidance is present (the route template 'Use [skill-name](relative/path/to/SKILL.md) to perform a specific task.', the exact path '.codex/skills/<skill-name>/', and condition-scoped links to real reference files), with the main gap being that 'Run the default skill validator' names no executable command.

4 / 5

Workflow Clarity

The 10-step workflow is clearly sequenced and backed by an explicit completion-criteria checklist and acceptance scenarios, but validation checkpoints are named rather than executable (no validator command, no explicit fix-and-revalidate loop), so it sits just below the anchor requiring explicit validation steps with feedback loops.

4 / 5

Progressive Disclosure

Three one-level-deep references in references/ (caddy-security.md, hierarchy-contract.md, diagram-contract.md) are each well-signaled with a condition for when to read them and all exist on disk, but the dense ~165-line body inlines substantial contract and routing policy that could be split out, leaving minor organization gaps relative to the ideal overview-plus-references split.

4 / 5

Total

15

/

20

Passed

Description

67%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 solid description with an explicit Use-for clause and multiple concrete actions, weakened by jargon-heavy trigger terms ('source grounding', 'session-derived guidance') that users would rarely say and by semi-abstract objects that blur exactly what gets created or audited.

Suggestions

Replace jargon triggers with natural phrases users would actually say, e.g. 'Use when writing, updating, or reviewing SKILL.md files, wiring up skill routing in AGENTS.md, or deciding which skill should own a piece of guidance'.

Make the 'what' more concrete by naming the artifacts touched, such as '.codex/skills/<name>/SKILL.md frontmatter, route statements in AGENTS.md, and reference files'.

Add common synonyms ('SKILL.md', 'skill metadata', 'frontmatter') so the description matches the varied ways users refer to skill authoring.

DimensionReasoningScore

Specificity

The description lists several concrete actions ("Create, port, revise, or audit repo-local skills") against named objects ("metadata, engineering contracts, and task routes"), but the objects are semi-abstract and coverage of what each action entails has minor gaps, matching the 'several specific actions; minor gaps' anchor rather than the fully comprehensive one.

4 / 5

Completeness

It has both a clear 'what' (create, port, revise, audit repo-local skills and their metadata) and an explicit 'Use for ...' when-clause, but the trigger phrases are abstract rather than concrete user-sayable conditions, so it does not reach the anchor requiring explicit concrete trigger phrases.

4 / 5

Trigger Term Quality

The trigger clause names some relevant keywords ("skill discovery", "ownership") but relies on jargon phrases like "source grounding" and "session-derived guidance" that users would not naturally say, and misses common variations such as "SKILL.md", "write a skill", or "update skills".

3 / 5

Distinctiveness Conflict Risk

The repo-local skill-authoring niche with its distinct trigger set is clearly distinguishable from unrelated skills, with only minor overlap risk against generic skill-discovery or documentation skills.

4 / 5

Total

15

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing, 1 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
greenpau/caddy-security
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.