CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

release-video

Turn a product release (the list of shipped items plus real screen recordings) into a motion recap video and one explained demo per feature, with sound effects tied to on-screen motion and a composed music bed. Use when asked for a release video, a changelog video, a feature recap reel, or demo clips for release notes and docs.

Quality

77%

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/release-video/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

43%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 a lean but hollow delegation stub: it defers to an external 'authoritative playbook' whose path is circular back to this same SKILL.md, and to `.agents/` files that are not part of any bundle present here. A reader cannot reach the actual release-video instructions, leaving the skill without usable content.

Suggestions

Replace the circular pointer to `.claude/skills/release-video/SKILL.md` with the actual workflow instructions inlined in the body, or bundle the playbook content under references/ and link to it with a real relative path.

Add concrete, executable guidance for the release-video workflow (steps for ingesting the changelog and screen recordings, assembling the recap and per-feature demos, and validation checkpoints before producing outputs) instead of 'execute it exactly as written'.

If `.agents/rules/cog.md` and `.agents/agents/<name>.md` are environment-specific machinery, verify they exist at the referenced paths or move that substitution logic into the referenced playbook so the SKILL.md body stands alone.

DimensionReasoningScore

Conciseness

The body is ~70 words with zero padding and no explanation of concepts Claude already knows — every sentence is an instruction. This matches anchor 5 ('Lean and efficient; assumes Claude's competence'); it is not 4 because there is no over-explanation to trim, and the lean problem with the body is substance, not token waste.

5 / 5

Actionability

The only guidance is 'Read `.claude/skills/release-video/SKILL.md` and execute it exactly as written' — a pointer, not steps, and that path is this same skill (name: release-video), making it circular. This matches anchor 2 ('Minimal concrete guidance; high-level hints but missing the specific steps to execute'); it is not 3 because there is no partially-executable instruction for the actual task, and not higher because no concrete commands or examples exist in the body.

2 / 5

Workflow Clarity

A rough two-step sequence exists (execute the playbook, then follow `.agents/rules/cog.md`) plus a conditional substitution rule, but the steps are poorly defined, delegate everything to unreachable files, and include no validation checkpoints. This matches anchor 2 ('Rough sequence present but many gaps; steps poorly defined; validation absent'); it is not 3 because no actual step of the video-production workflow is listed anywhere.

2 / 5

Progressive Disclosure

The body references `.claude/skills/release-video/SKILL.md` (circular — this is the same skill's own file), `.agents/rules/cog.md`, and a wildcard `.agents/agents/<name>.md`, none of which exist in any bundle directory (references/, scripts/, assets/ are all absent). This mirrors the anchor-1 failure mode of nested/circular references where the actual instructions are unreachable, 'impossible to navigate'; it is not 2 because the problem is not inlining but that no referenced content can be located at all.

1 / 5

Total

10

/

20

Passed

Description

100%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 exemplary: it names concrete deliverables (recap video, per-feature demos, motion-tied sound effects, music bed) and provides an explicit, multi-synonym trigger clause in third-person declarative voice with no padding. Both 'what' and 'when' are answered clearly and distinctly from other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions with comprehensive coverage of the domain's outputs: 'motion recap video and one explained demo per feature, with sound effects tied to on-screen motion and a composed music bed'. This matches the anchor 'Lists multiple specific concrete actions; comprehensive coverage' — not 4, since there are no meaningful gaps in what the skill produces, and not below since every capability is concrete rather than generic.

5 / 5

Completeness

It explicitly answers both questions: the 'what' is the full production pipeline described up front, and the 'when' is a concrete 'Use when asked for a release video, a changelog video, a feature recap reel, or demo clips' clause. This matches anchor 5 ('Clearly and explicitly answers both what AND when with concrete trigger phrases'), not 4, because the 'when' clause is already fully explicit and specific.

5 / 5

Trigger Term Quality

The 'when' clause covers natural synonyms users would say: 'release video, a changelog video, a feature recap reel, or demo clips for release notes and docs'. This is comprehensive coverage including variations, matching anchor 5; anchor 4 ('a few natural terms missing') would require an obviously absent common phrasing, which is not the case here.

5 / 5

Distinctiveness Conflict Risk

The release-recap-video niche with its trigger phrases ('changelog video', 'feature recap reel') is clearly distinct from generic video or documentation skills. It matches anchor 5 ('Clear niche with distinct triggers; minimal conflict risk'); a 4 would imply notable overlap with a closely related skill, which the specific triggers here avoid.

5 / 5

Total

20

/

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/release-video/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.