CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

rendered-pack-6e1e24d4

Use when working in the MoltNet codebase on Drizzle repository patterns, transactions, migrations, the auth plugin (optionalAuth team context), consolidate workflow diary-ownership checks, ogen CLI multi-status responses, pack provenance, or e2e tests.

52

Quality

66%

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 ./.agents/skills/rendered-pack-6e1e24d4/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 lean, information-dense context pack: nearly every line carries non-obvious, repo-specific guidance with exact file paths and commands, and only small amounts of narrative padding. Its main weaknesses are the absence of verification checkpoints in the database/auth directives (only migrations get an explicit check-and-patch loop) and one dangling reference to a 'database layer tile' that does not exist in the bundle.

Suggestions

Add explicit verification steps to the fix directives — e.g., after the diaryId fix, confirm with a cross-tenant test that `list({ ids })` with a foreign entryId returns nothing; after `pnpm db:generate`, run the journal monotonicity check as a numbered step — to lift workflow clarity past the database feedback-loop cap.

Resolve the 'database layer tile' reference: either inline the tile's key points (it is the claimed home of the repository factory pattern and hybrid search details) or remove the mention, since no bundle files exist.

Show the two highest-value fix patterns as short snippets — the ogen 200/201 type switch and the `getTableColumns` embedding exclusion — to make the guidance copy-paste ready.

DimensionReasoningScore

Conciseness

The body is dense with repo-specific, non-obvious facts (DBOS/AsyncLocalStorage transaction context, synthetic monotonic timestamps '1774560400000+N', embedding column exclusion) and never explains concepts Claude already knows. Minor trimmable padding remains: the exploit narrative in the consolidate section, 'PR #667 revealed that...', and the provenance table. This fits anchor 4 (efficient, minor over-explanation that could be trimmed); it is below anchor 5 because those narrative and metadata passages do not all earn their place.

4 / 5

Actionability

Mostly executable guidance with concrete commands and exact paths: 'MUST run `pnpm db:generate` immediately after every change to `libs/database/src/schema.ts`', 'Pass `diaryId` alongside `ids`', 'check that the generated `when` value in `libs/database/drizzle/meta/_journal.json` is strictly greater than the previous entry's value. Patch manually if needed'. It falls short of anchor 5 because key fixes are described rather than shown (e.g., 'a type switch handling both variants' for the ogen 201 case, and the getTableColumns embedding-exclusion pattern have no code snippet).

4 / 5

Workflow Clarity

Only the migration section provides an explicit validate-and-fix loop (generate → check journal `when` monotonicity → patch manually). The other database and auth directives prescribe fixes without verification steps — no test confirmation for the diaryId cross-tenant fix, no checkpoint for the db:generate rule itself, no run step for e2e coverage — leaving checkpoints implicit, which matches anchor 3 and is capped there by the feedback-loop rule for database operations. It is above anchor 2 because each individual directive is unambiguous and the migration loop is genuinely sequenced.

3 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and at ~60 lines the body is appropriately self-contained with clear topic sections — close to the 'well-organized sections' ideal. It falls short of anchor 5 because the line 'are covered in the database layer tile' references external content that is not present in the bundle, a minor navigation gap. It is above anchor 3 because the structure is good and the bulk of the content is rightly inline.

4 / 5

Total

15

/

20

Passed

Description

51%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 well-scoped and distinctive, with strong codebase-specific trigger terms, but it is only a 'when' clause: it never states what the skill does or lists any capability actions, leaving the 'what' half of completeness entirely missing.

Suggestions

Add a leading 'what' clause stating the skill's function, e.g. 'Provides repo-specific database, CLI, and auth patterns and post-mortem fixes for the MoltNet codebase. Use when...' — this directly fixes the completeness gap.

Include concrete actions in the 'what' clause (e.g., 'apply getExecutor transaction patterns, keep migration journal timestamps monotonic, resolve optionalAuth team context') instead of listing only topic nouns, to raise specificity.

Add natural synonyms users would say — 'database schema', 'API client tests', 'ogen 201 response' — alongside the internal jargon to broaden trigger coverage.

DimensionReasoningScore

Specificity

The description names many concrete domains ('Drizzle repository patterns, transactions, migrations, the auth plugin (optionalAuth team context), consolidate workflow diary-ownership checks, ogen CLI multi-status responses') but contains no capability actions at all — the only verb is 'Use when working', so it never states what the skill does. This matches anchor 2 (domain named, actions minimal/absent); it is above anchor 1 because the domains are technically concrete, and below anchor 3 because no 'what' actions are listed.

2 / 5

Completeness

The description is entirely a 'when' clause ('Use when working in the MoltNet codebase on...') with no 'what' — what the skill provides (context patterns? fixes? conventions?) is never stated and must not be inferred per the guidelines. This matches anchor 2 ('only when is present without what'); it is not anchor 1 because the 'when' is detailed and specific.

2 / 5

Trigger Term Quality

Strong natural keywords a MoltNet developer would actually say: 'transactions', 'migrations', 'auth plugin', 'e2e tests', 'Drizzle'. A few terms are internal jargon rather than natural user phrasing ('pack provenance', 'ogen CLI multi-status responses', 'consolidate workflow diary-ownership checks') and common synonyms are missing ('database schema', 'API client'), so it sits between anchors 4 and 5, closer to 4.

4 / 5

Distinctiveness Conflict Risk

Scoped by codebase name ('MoltNet codebase') and highly specific internal components (optionalAuth team context, consolidate workflow, ogen CLI, Drizzle repositories), giving it a clear niche with distinct triggers and minimal conflict risk with any generic skill.

5 / 5

Total

13

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 8 missing

Warning

Total

14

/

16

Passed

Repository

getlarge/themoltnet

Path

.agents/skills/rendered-pack-6e1e24d4/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.