gifgrep

Search GIF providers with CLI/TUI, download results, and extract stills/sheets.

2.16x

Quality

76%

Does it follow best practices?

Impact

93%

2.16x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./openclaw/skills/gifgrep/SKILL.md

The canonical home for this skill is gifgrep in Hung-Reo/hungreo-openclaw

Quality

Content

93%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 an exemplary lean, command-first reference: executable examples for every capability, well-labeled sections, no padding, and no unnecessary bundle files. The only notable gap is that the search→download→extract pipeline is stated but never connected end-to-end (download location vs. the './clip.gif' input used in extraction examples), which costs a workflow checkpoint.

Suggestions

Bridge the download→extract stages: show how to reference the file saved to ~/Downloads in the still/sheet commands (e.g. 'gifgrep still ~/Downloads/<name>.gif --at 1.5s'), including a quick existence check after --download.

Note the platform constraint on '--reveal' (Finder is macOS-only) so non-macOS users aren't misled.

Reconcile the invocation styles shown ('gifgrep search --json cats' vs 'gifgrep cats --json') so it is clear which argument order is canonical.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-driven — every line is an executable command, a flag fact, or an environment toggle, with zero explanation of concepts Claude already knows. This matches the 'every token earns its place' anchor.	5 / 5
Actionability	Quick start and each section provide copy-paste-ready commands covering the common cases: search ('gifgrep cats --max 5'), JSON output ('gifgrep search --json cats \| jq ...'), piping ('--format url'), TUI ('gifgrep tui'), still and sheet extraction with tunable flags. This matches the fully-executable anchor.	5 / 5
Workflow Clarity	The pipeline is explicitly stated ('Search → preview → download → extract (still/sheet)') and sections map to those stages, matching 'clear sequence with most checkpoints'. It is not 5 because the stages are not linked: downloads go to '~/Downloads' with no example of locating the downloaded file, while the still/sheet examples use './clip.gif' — a disconnect with no verification checkpoint bridging download to extraction.	4 / 5
Progressive Disclosure	The skill is under 50 lines with no external references needed; sections are well-organized and clearly labeled. Per the rubric's simple-skill scoring note, this warrants a 5 with just well-organized sections.	5 / 5
	Total	19 / 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 concise and names concrete capabilities in a distinct niche, but it omits any 'when to use' trigger guidance and misses natural trigger vocabulary (Tenor, Giphy, reaction GIF, animated). The compressed jargon 'stills/sheets' also narrows its discoverability.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to find, download, or grab frames from a GIF (Tenor/Giphy), or needs a reaction GIF, still frame, or contact sheet.'

Include natural synonyms users actually say — Tenor, Giphy, reaction GIF, animated images, .gif — to improve trigger-term coverage.

Expand 'stills/sheets' once (e.g. 'extract still frames or contact sheets') so the capability is unambiguous to both users and Claude.

Dimension	Reasoning	Score
Specificity	The description names the domain ("GIF providers") and several concrete actions ("Search ... with CLI/TUI", "download results", "extract stills/sheets"), matching the 'several specific actions with minor gaps' anchor. It falls short of 5 because 'stills/sheets' and 'CLI/TUI' are compressed jargon and coverage is not fully comprehensive.	4 / 5
Completeness	The 'what' is clear (search GIF providers, download, extract stills/sheets), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the judging guidelines state caps completeness at 3. It is not 2 because the 'what' is concrete, not vague.	3 / 5
Trigger Term Quality	"GIF", "Search", and "download" are relevant keywords a user might say, but common natural variations are missing — no "Tenor", "Giphy", "reaction GIF", "animated", or ".gif". This matches 'some relevant keywords but missing common variations or synonyms' rather than the good-coverage anchor at 4.	3 / 5
Distinctiveness Conflict Risk	The GIF-provider-search/still-extraction niche is clearly distinct from most skills, with minor overlap risk only against general image-search or media-download skills. It lacks the explicit trigger phrases of the 5 anchor but is well above the overlap risk of anchors 2-3.	4 / 5
	Total	14 / 20 Passed

Validation

81%

Warnings & errors only

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

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
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	13 / 16 Passed

Repository: trpc-group/trpc-agent-go
Path: openclaw/skills/gifgrep/SKILL.md
Commit: 9bb1c42

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.