CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ai-subtitle-remover

550W Watermark & Text Eraser: remove image text/watermarks, local video subtitles/visual watermarks, and platform watermarks from TikTok or X share links. OAuth MCP or API Key access depends on the host.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./SKILL.md

The canonical home for this skill is ai-subtitle-remover in sunshinehu/550w-ai-subtitle-remover

SKILL.md
Quality
Evals
Security

Quality

Content

75%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, security-conscious overview that gives concrete commands, exact parameter names, and explicit failure/consent checkpoints while deferring route-specific workflows to real bundled reference files. The main improvement opportunities are de-duplicating the fallback/approval statements and surfacing the api-contract and agent-compatibility references from the root.

DimensionReasoningScore

Conciseness

Dense, policy-only prose that assumes Claude's competence and explains no known concepts, but with minor repetition that could be trimmed: the resolved-download-failure fallback appears in both the Capabilities section and 'Files and results', and the approval/consent requirement is stated both in 'Files and results' and again in the closing confirmProcessing paragraph. Efficient with minor trims available — not 5.

4 / 5

Actionability

Includes a fully executable example ('node {baseDir}/dist/550w-skill.cjs' with a concrete JSON stdin payload), exact endpoint URLs, env var names, and parameter names (confirmProcessing=true, x1/y1/x2/y2, params.region="global"); remaining operational detail is deliberately deferred to the workflow references. Minor gaps (e.g. dist/550w-skill.cjs is not present in this bundle's scripts/) keep it below fully copy-paste-ready 5.

4 / 5

Workflow Clarity

Route selection is a numbered decision sequence with explicit failure checkpoints (download timeout → return resolved URL; 401/expiry/insufficient-credit handling; 'If acceptance is unknown, check the original task'), and confirmProcessing gates every paid submission. The main upload→submit→retrieve sequence itself is not stepped in the body but deferred to the workflow references — a minor gap, so not 5. No destructive/batch cap applies since validation checkpoints are present.

4 / 5

Progressive Disclosure

Clear overview with well-signaled, one-hop markdown links to references/oauth-access.md and references/openapi-access.md (both present in the bundle), with detail appropriately split out. Minor gaps: api-contract.md and agent-compatibility.md are only reachable via a second hop from openapi-access.md rather than from the root, and that chain makes references effectively two levels deep — good structure but not the clean one-level navigation of 5.

4 / 5

Total

16

/

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, distinctive description that names its concrete capabilities well, but it never tells Claude when to activate it — no 'Use when...' trigger clause, which caps completeness at 3. Adding an explicit trigger sentence and a few natural synonyms (captions, erase, .mp4) would round it out.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user wants to remove watermarks, subtitles/captions, or unwanted text from images or videos, or clean a TikTok/X share link.'

Add natural synonyms users would say: 'captions', 'erase text', 'clean up video', and file extensions like '.mp4' or '.mov' to broaden trigger matching.

Drop the trailing access-route sentence ('OAuth MCP or API Key access depends on the host') from the description — it is configuration detail, not capability or trigger information, and spends the description budget without improving triggering.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions covering the skill's full capability surface: 'remove image text/watermarks, local video subtitles/visual watermarks, and platform watermarks from TikTok or X share links' — comprehensive coverage with no gaps, matching the top anchor rather than the 'minor gaps' of 4.

5 / 5

Completeness

The 'what' is clear and specific, but there is no 'Use when...' clause or equivalent explicit trigger guidance anywhere in the description; the judging guideline caps completeness at 3 in that case. Not 4, because 'when' is entirely absent rather than merely imprecise; not 2, because the 'what' is fully concrete.

3 / 5

Trigger Term Quality

Good natural keyword coverage ('watermark', 'remove', 'subtitles', 'image text', 'TikTok', 'X', 'share links'), but common synonyms and variations are missing — no 'captions', 'erase text', 'clean video', or file extensions like '.mp4'. Fits 'good keyword coverage; a few natural terms missing', not the comprehensive synonym coverage of 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche (550W watermark/subtitle/text erasure) with distinct triggers including platform names (TikTok, X share links); minimal conflict risk with other skills, matching the top anchor.

5 / 5

Total

17

/

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_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

sunshinehu/550w-ai-subtitle-remover

Path

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.