CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

kb-ingest

Ingest a source into the wiki — read it in full, compile durable cited pages, and update the index, log, and overview in one commit. Accepts files in raw/, URLs to fetch and archive first, a directory of a code repo read in place, or the answer /kb-ask just gave. Use when the user says ingest, compile this source, add this to the wiki, or pastes a link to read into it.

Quality

91%

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

88%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-crafted instruction-only skill body: an 11-step protocol with real validation checkpoints and failure reporting, concrete file paths, citation formats, and commit conventions, with no filler or concept explanations. The two minor weaknesses are slight rule duplication and three inlined step-0 sub-procedures that could live in separate reference files.

DimensionReasoningScore

Conciseness

Dense and imperative throughout with no explanations of concepts Claude already knows, but contains minor duplication that could be trimmed: the 'support: one-source' rule appears in two separate rule bullets, and 'Preserve the source's own claim' overlaps 'Preserve the source's language'. This fits anchor 4 (efficient, minor instances of over-explanation) rather than 5, where every token earns its place with no repeated rules.

4 / 5

Actionability

Fully executable instruction-level guidance: exact file paths ('raw/YYYY-MM-DD-slug.md', 'wiki/sources/<slug>.md', 'wiki/questions/YYYY-MM-DD-<slug>.md'), a concrete citation format ('<repo>@<sha>:<path>:<line>'), specific commands ('git show <sha>:<path>', 'git status'), an exact commit message format ('kb(ingest): <source title>'), and explicit anti-patterns ('Never use git add .'). Per the rubric's scoring notes, absence of code in an instruction-only skill is not penalized when guidance is this actionable.

5 / 5

Workflow Clarity

Steps 0–10 are clearly sequenced with explicit validation checkpoints and feedback loops: inspect git status before editing, ask before combining uncommitted edits, report failed or truncated fetches rather than inventing archives, review the diff for secrets before committing, and an explicit failure path ('record that in log.md as left open — never leave it silent'). Validation is present, so the batch-operation cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist; the single body is well-organized into Boundaries / Protocol / Rules with clear section headers, so navigation is easy. However, at ~120 lines with three sub-procedures inlined in step 0 (URL handling, pinned code reads, and a full last-answer paragraph that is a candidate for its own reference file), it fits anchor 4 (good structure, minor organization gaps) rather than 5 — the under-50-lines exception does not apply.

4 / 5

Total

18

/

20

Passed

Description

92%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: third-person, concrete about the full pipeline (read, compile cited pages, update index/log/overview, one commit), explicit about all input types, and closing with an explicit 'Use when' clause containing natural trigger phrases. The only weakness is trigger coverage stopping short of common synonyms such as 'archive this' or 'knowledge base'.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'read it in full, compile durable cited pages, and update the index, log, and overview in one commit' — and enumerates all four accepted input types, giving comprehensive coverage of the operation. Anchor 4 would require minor gaps in coverage, but the read/compile/update/commit pipeline plus input handling is complete.

5 / 5

Completeness

Explicitly answers both what ('read it in full, compile durable cited pages, and update the index, log, and overview in one commit') and when ('Use when the user says ingest, compile this source, add this to the wiki, or pastes a link'), with concrete trigger phrases matching the top anchor exactly.

5 / 5

Trigger Term Quality

Provides four natural trigger phrases users would say: 'ingest, compile this source, add this to the wiki, or pastes a link to read into it'. Coverage is good but not comprehensive — common variations like 'archive this', 'save/remember this source', or 'knowledge base' are missing, so it sits between anchors 3 and 5, noticeably above the midpoint.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (wiki ingestion pipeline, integration with /kb-ask, wiki-specific triggers like 'add this to the wiki') with distinct trigger terms and minimal conflict risk against other skills.

5 / 5

Total

19

/

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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

bibryam/minimal-karpathy-llm-wiki-skill

Path

skills/kb-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.