CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

wiki-ingest

Ingest a source file from raw/ into the LLM Wiki — read, discuss, write summary page, update cross-references across 5-15 pages, regenerate index, append to log. Usage /wiki-ingest <path-to-source>

Quality

81%

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

78%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 tight, actionable command document: an 8-step sequenced workflow with a user-confirmation gate, concrete script commands, and well-signaled one-level references. Remaining gaps are minor — duplicated script paths, missing arguments for two script invocations, and no explicit error-recovery guidance.

Suggestions

Show full invocations with arguments for ingest_source.py and update_index.py (as append_log.py already does) so every step is copy-paste executable.

Add a brief error-recovery note for likely failure points, e.g., what to do when the prep script cannot parse the source or when merge-mode finds conflicting claims.

Drop the duplicate "Scripts" section (or the inline script mentions in "What happens") to remove the repeated long paths.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no explanations of known concepts. Minor redundancy keeps it at anchor 4 rather than 5: the three long script paths are repeated in both "What happens" and "Scripts", and "5-15 pages" is stated in both the intro and the flow line.

4 / 5

Actionability

Concrete, mostly executable guidance: usage examples with real paths ("/wiki-ingest raw/papers/monosemanticity.pdf") and a full command with arguments ("append_log.py --op ingest --title \"<title>\""). Anchor 4 rather than 5 because invocations for ingest_source.py and update_index.py omit their arguments.

4 / 5

Workflow Clarity

Steps 1-8 are clearly sequenced and include an explicit user-confirmation checkpoint ("Confirm — waits for your go-ahead") before the batch 5-15-page write, so the batch-operation cap does not apply. It is anchor 4 rather than 5 because there is no error-recovery loop (e.g., what to do if prep fails or a merge-mode conflict arises) and no final verification checklist.

4 / 5

Progressive Disclosure

The ~49-line body is a clear overview with well-signaled, one-level-deep references ("See agents/wiki-ingestor.md", "→ engineering/llm-wiki/skills/llm-wiki/references/ingest-workflow.md") and clean section organization. No nested references exist, and no bundle directories ship with this copy, so the references point to the canonical copy's tree — matching anchor 5 for a short, well-organized skill.

5 / 5

Total

17

/

20

Passed

Description

75%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 specific, third-person, action-dense description with strong distinctiveness. Its main weakness is the absence of an explicit "Use when..." trigger clause, leaving the "when" only weakly implied by the usage syntax, and a lack of natural synonyms beyond "ingest".

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases, e.g., "Use when adding a new source to the wiki, re-ingesting an updated paper, or when the user says ingest/add/import a source".

Include natural synonyms users might say ("add a paper", "import a source", "summarize an article into the wiki") alongside "ingest" to broaden trigger coverage.

State when NOT to use it (e.g., for editing an existing wiki page rather than ingesting a new raw source) to further reduce conflict with adjacent wiki commands.

DimensionReasoningScore

Specificity

The description lists six concrete actions — "read, discuss, write summary page, update cross-references across 5-15 pages, regenerate index, append to log" — in third person, giving comprehensive coverage of the skill's capabilities. It matches anchor 5 rather than 4 because no meaningful action in the domain is omitted.

5 / 5

Completeness

The "what" is clearly and explicitly answered by the full action list, but the "when" is only weakly implied by "Usage /wiki-ingest <path-to-source>", which is invocation syntax rather than trigger guidance. Per the rubric guideline, a missing "Use when..." clause (or equivalent explicit trigger guidance) caps completeness at 3; it is not 4 because no explicit trigger conditions exist anywhere in the description.

3 / 5

Trigger Term Quality

Natural domain keywords are well covered: "ingest", "source file", "raw/", "LLM Wiki", "summary page", "cross-references", "index", "log". It falls short of anchor 5 because common synonyms and variations a user might say ("add", "import", "summarize a source", "update the wiki") are absent.

4 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche with distinct triggers — "raw/" layer, "LLM Wiki", "summary page", "index", "log" — that no other generic skill would claim. Conflict risk is minimal, matching anchor 5.

5 / 5

Total

17

/

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

alirezarezvani/claude-skills

Path

.gemini/skills/wiki-ingest/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.