CtrlK
BlogDocsLog inGet started
Tessl Logo

index-refresh

Use when an LLM Wiki operation issue requests an index refresh. Rebuild `wiki/index.md` from the actual wiki tree, reconcile missing/deleted entries, and log counts without editing page bodies.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

90%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 exemplary instruction-only skill body: a tightly written, concrete 9-step workflow with exact output formats, explicit non-goals, and a verification checklist that gates issue closure. The only structural weaknesses are the absence of an explicit error-recovery loop for the batch write, and a length just past the threshold where the rubric would award full progressive-disclosure credit without bundle files.

DimensionReasoningScore

Conciseness

The body is lean and fully operational: every section (Inputs, Workflow, NOT-do, Voice, Verification, Tools) issues instructions rather than explaining concepts Claude already knows, and the one framing sentence ("the index is the maintainer's first stop for navigation") earns its place by stating the goal. It matches the 'every token earns its place' anchor; not the 4 anchor, which requires trimmable over-explanation — none is evident.

5 / 5

Actionability

Guidance is fully executable for an instruction-only skill: exact entry format (`- [[<path>]] — <one-line summary>`), exact log-entry templates with field placeholders, concrete paths (`wiki/projects/<slug>/standup.md`, `wiki/log.md`), explicit skip rules, and named tools with their allowed write targets. This matches the 5 anchor ('copy-paste ready... specific examples cover the common cases'); the 4 anchor's 'minor gaps' do not apply.

5 / 5

Workflow Clarity

The 9-step workflow is clearly sequenced (read index, walk by category, scan the last ~50 log entries, produce sorted entries, drop dead entries, add missing ones, write editorially, preserve custom categories, append counts) and closes with an explicit pre-close Verification checklist covering the batch-write risks (dangling entries, modified page bodies). It falls short of the 5 anchor because there is no explicit validate→fix→retry feedback loop for this batch file-writing operation — the checklist gates closing the issue but does not tell the agent what to do when a check fails.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), and the ~60-line body is appropriately self-contained with well-labeled sections — the rubric's 5-without-references exception is reserved for skills under 50 lines, which this slightly exceeds, so the 4 anchor ('good structure; most content appropriately placed; minor organization gaps') is the best fit. It is clearly above the 3 anchor: nothing that belongs in a separate file is inlined.

4 / 5

Total

18

/

20

Passed

Description

76%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 an explicit 'Use when' trigger, concrete rebuild/reconcile/log actions, and a clear non-goal boundary. Its main weakness is trigger vocabulary: the keywords are system-internal jargon rather than the natural phrases a user would say, so natural-language variations are missing.

Suggestions

Add natural trigger phrasings users might actually say, e.g. 'Use when the user asks to update, rebuild, or sync the wiki index, or when wiki pages are missing from or linger in `wiki/index.md`.'

Name the durable artifacts more fully in the trigger (e.g. mention project standup pages or custom categories) so the description's coverage matches the body's workflow.

Add a one-clause contrast with the adjacent `wiki-lint` routine (index reconciliation vs. contradiction/link repair) to further reduce overlap risk.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "Rebuild `wiki/index.md` from the actual wiki tree", "reconcile missing/deleted entries", "log counts without editing page bodies" — plus an explicit non-goal boundary. It falls just short of the 5 anchor because it omits part of the workflow covered in the body (e.g. walking categories, preserving custom sections), a minor coverage gap.

4 / 5

Completeness

Both questions are answered explicitly: "Use when an LLM Wiki operation issue requests an index refresh" gives a concrete when-clause, and the rebuild/reconcile/log actions with the "without editing page bodies" boundary give a clear what. It clearly matches the 5 anchor rather than the 4 anchor, whose 'when' is only partially explicit.

5 / 5

Trigger Term Quality

Relevant keywords are present ("index refresh", "LLM Wiki", "operation issue", "wiki/index.md") but they are domain-jargon heavy and miss natural user variations like "update/rebuild/sync the index", "index is out of date", or "standup". This sits between "some relevant keywords but missing common variations" (3) and "good keyword coverage" (4), closer to 3 because the natural-language phrasings a user would actually say are largely absent.

3 / 5

Distinctiveness Conflict Risk

The trigger is a narrow niche (an LLM Wiki operation issue specifically requesting an index refresh), making wrong-skill firing unlikely, though the description does not contrast itself with the closely related `wiki-lint` routine mentioned in the body, leaving minor overlap risk. Mostly distinct with minor overlap — the 4 anchor.

4 / 5

Total

16

/

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
paperclipai/paperclip
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.