CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

index-at-creation

Index at Creation Time

Quality

60%

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 ./.claude/skills/index-at-creation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

The body is a tight, well-organized pattern statement: a clear principle, concrete DO/DON'T directives, and identifiable provenance. Its main weakness is that the concrete directions (hook name, --file flag) never assemble into an executable command or example, leaving the 'how' to inference. The non-operational Source Sessions section is minor token overhead.

Suggestions

Add one executable example, e.g. the actual indexing command invoked in the PostToolUse Write hook (including the tool name behind `--file`), so the guidance is copy-paste ready.

Show a minimal hook configuration or command line demonstrating 'trigger indexing from the same event that creates the artifact'.

Drop or compress the Source Sessions section (session IDs a541f08a, 1c21e6c8 add no operational value), or move provenance out of the runtime body.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — "Index artifacts when they're created, not at batch boundaries" plus terse DO/DON'T bullets with no concept explanations. It falls just short of anchor 5 because the "Source Sessions" section ("a541f08a", "1c21e6c8") is non-operational provenance padding that could be trimmed, matching anchor 4 ('minor instances... that could be trimmed').

4 / 5

Actionability

Guidance is directionally concrete — "Index handoffs in PostToolUse Write hook", "Use `--file` flag" — but never gives an executable command or hook configuration, so key details are missing (which indexer, what invocation). This matches anchor 3 ('Some concrete guidance but incomplete... missing key details'); not 4 because nothing here is copy-paste executable or spec-complete.

3 / 5

Workflow Clarity

As a simple single-purpose skill, the single action is clearly stated from three reinforcing angles: index in the PostToolUse Write hook 'immediately after creation', 'Trigger indexing from the same event that creates the artifact', and the DON'T items fence off the wrong paths (SessionEnd batching, cron). It sits at anchor 4 rather than 5 because no example hook implementation or verification that indexing succeeded is shown — a minor gap, not an incoherent or unsequenced process.

4 / 5

Progressive Disclosure

The skill is under 50 lines, self-contained, needs no external references (none exist in references/, scripts/, or assets/), and is organized into clear sections (Pattern, DO, DON'T, Source Sessions). Per the simple-skill guideline this matches anchor 5 — well-organized sections with nothing that should be split out.

5 / 5

Total

16

/

20

Passed

Description

28%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.

The description is a bare title fragment rather than a capability description. It conveys a domain concept but no concrete actions, no trigger terms, and no 'when to use' guidance, so it would rarely surface at the right moment. It reads like a heading, not a deployable skill description.

Suggestions

Rewrite as a third-person capability sentence, e.g. 'Indexes artifacts immediately when they are created (via PostToolUse Write hooks) rather than at batch boundaries. Use when downstream logic depends on newly created artifacts being queryable right away.'

Add a 'Use when...' clause with natural trigger phrases users would actually say, such as 'indexing', 'real-time search', 'make artifacts queryable', or 'don't wait for SessionEnd'.

List 1-2 concrete actions (e.g. single-file indexing with a --file flag) so the description communicates what the skill actually does, not just its topic.

DimensionReasoningScore

Specificity

The description is only the fragment "Index at Creation Time" — it names the indexing domain and contains one minimal action ("Index"), matching anchor 2 ('Names the domain but actions are minimal or generic'). It is above anchor 1 because "Index" is a concrete action tied to a specific timing ('at Creation Time'), but below anchor 3 since no verb-phrase list of capabilities exists.

2 / 5

Completeness

"Index at Creation Time" gives a vague 'what' (indexing, timed at creation) and has no 'when to use' clause at all, exactly matching anchor 2 ('Has a vague what and no when'). Not 1 because the timing qualifier conveys slightly more than 'Helps with documents'; not 3 because even the 'what' is a title fragment, not a stated capability, and the missing 'Use when...' clause caps this dimension regardless.

2 / 5

Trigger Term Quality

Only "Index" and "Creation" are present — one or two keywords with no natural phrases a user would say (e.g. 'indexing', 'real-time indexing', 'when artifacts are created'), matching anchor 2. Not 3 because common variations and synonyms are entirely absent, not merely incomplete.

2 / 5

Distinctiveness Conflict Risk

The timing-specific framing ('at Creation Time') carves out a niche versus generic indexing skills, but with no trigger phrases or elaboration it could still overlap with any indexing-related request, matching anchor 3 ('Somewhat specific but could still overlap with similar skills'). Not 4 because nothing distinguishes it from sibling indexing skills in the user's own words.

3 / 5

Total

9

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

parcadei/Continuous-Claude-v3

Path

.claude/skills/index-at-creation/SKILL.md

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.