CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

content-factory

Autonomous content pipeline - scout announcements in your field, triage by trend momentum and personal angle, produce posts/blogs/videos in your voice with ledger-based dedup, hard volume caps, and screenshot-verified publishing

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/content-factory/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 extremely lean but functions purely as a redirect to another SKILL.md, so it contributes little standalone executable guidance, workflow sequencing, or progressive disclosure. The actual skill substance is not self-contained in this file.

Suggestions

Inline at least a minimal quick-start summary of the pipeline steps (scout → triage → produce → publish) so the body is actionable without resolving the external playbook.

Add an explicit validation/checkpoint step for the batch publishing operation (e.g. verify the ledger dedup and volume cap before publishing) to lift workflow clarity above 3.

If the delegated SKILL.md is the authoritative source, surface its key sections as clearly signaled one-level-deep references within this skill's own bundle rather than an opaque external path.

DimensionReasoningScore

Conciseness

The body is four lean lines — 'Read ... SKILL.md and execute it exactly as written' plus the antigravity substitution rule — with no padding and every token earning its place.

5 / 5

Actionability

It gives a concrete directive ('execute it exactly as written') and a specific substitution rule, but the executable substance lives in the delegated external SKILL.md rather than in this body, so guidance is incomplete here.

3 / 5

Workflow Clarity

A rough sequence is present ('execute it ... Then follow .agents/rules/cog.md') with a conditional substitution, but the real workflow is external and there are no validation checkpoints for what is fundamentally a batch publishing operation.

3 / 5

Progressive Disclosure

There is minimal structure and no bundle files (references/scripts/assets absent); the body is a redirect to an external SKILL.md rather than an overview pointing to one-level-deep supporting material, so references are effectively buried outside the bundle.

2 / 5

Total

13

/

20

Passed

Description

58%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 specific and action-rich with a clear distinct niche, but it omits any explicit 'Use when...' trigger guidance and slips into second-person voice ('your field', 'in your voice'), capping completeness and reducing specificity. Adding a concrete trigger clause would lift both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user wants to plan, triage, and publish social content on a recurring schedule with dedup and volume limits.'

Rephrase to third person — replace 'your field'/'in your voice' with 'the user's field'/'their voice' — to satisfy the voice guideline.

Add natural synonyms users actually say ('content calendar', 'social posts', 'autopilot posting') alongside the existing jargon.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'scout announcements', 'triage by trend momentum and personal angle', 'produce posts/blogs/videos', 'ledger-based dedup', 'hard volume caps', 'screenshot-verified publishing' — which is comprehensive coverage; reduced from 5 to 4 because of second-person phrasing ('your field', 'in your voice') per the voice penalty.

4 / 5

Completeness

Clearly states 'what' the skill does (autonomous content pipeline with enumerated actions) but provides no 'when' / explicit trigger guidance, so completeness is capped at 3 per the missing-'Use when' guideline.

3 / 5

Trigger Term Quality

Contains some natural terms ('posts/blogs/videos', 'publishing', 'announcements') but leans on jargon ('ledger-based dedup', 'trend momentum') and lacks common synonyms or the natural phrases a user would say, with no 'Use when...' trigger clause.

3 / 5

Distinctiveness Conflict Risk

The niche framing — 'ledger-based dedup', 'hard volume caps', 'screenshot-verified publishing' — gives it a fairly distinct trigger surface with only minor overlap risk against generic content-creation skills.

4 / 5

Total

14

/

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

huytieu/COG-second-brain

Path

.agents/skills/content-factory/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.