CtrlK
BlogDocsLog inGet started
Tessl Logo

github-wayback-recovery

Recover deleted GitHub content using the Wayback Machine and Archive.org APIs. Use when repositories, files, issues, PRs, or wiki pages have been deleted from GitHub but may persist in web archives. Covers CDX API queries, URL patterns, and systematic recovery workflows.

63

Quality

75%

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 ./.claude/skills/oss-forensics/github-wayback-recovery/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 dense, actionable reference with clear per-scenario recovery workflows and executable curl/Python examples; its main weaknesses are token bloat from the inlined Python class and the absence of progressive disclosure via separate reference files for the CDX API and implementation detail.

Suggestions

Move the full Python implementation into a references/ file (e.g. references/recovery.py) and keep only a minimal usage snippet in SKILL.md to cut ~120 lines of inline code that duplicates the curl examples.

Extract the CDX API parameter table and response-format detail into a references/cdx-api.md, signaling it with a one-level-deep 'See [cdx-api.md]' link so SKILL.md reads as an overview.

Add an explicit verify checkpoint to each Investigation Pattern (e.g. 'Confirm statuscode:200 and a non-empty digest before constructing the archive URL') to turn the implicit validation into a clear feedback loop.

DimensionReasoningScore

Conciseness

Mostly efficient reference material (URL tables, CDX params, curl examples) that assumes Claude's competence, but the ~120-line Python class largely duplicates the curl examples and includes a hand-wavy 'simplified - would need HTML parsing' comment; a few transitional sentences ('Understanding GitHub's URL structure is essential...') could be trimmed.

3 / 5

Actionability

Copy-paste-ready curl commands, full URL-pattern tables, a working Python class with a usage example, and per-scenario command sequences; minor gaps remain in placeholder substitution ({TIMESTAMP}/{owner}/{repo}) and the simplified fork-extraction regex.

4 / 5

Workflow Clarity

Investigation Patterns give clear Step 1/2/3 sequences with concrete commands for file, issue/PR, fork, and wiki recovery; this is read-only OSINT (no destructive/batch cap applies) and includes light validation (filter=statuscode:200, HTTP code check for forks), though explicit verify-then-continue feedback loops are only implicit.

4 / 5

Progressive Disclosure

Well-sectioned body, but no bundle files exist and the bulk CDX API reference and full Python implementation are inlined in a ~400-line SKILL.md rather than split into one-level-deep reference files; the only external links are the 'Learn More' pointers.

3 / 5

Total

14

/

20

Passed

Description

87%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 tight, third-person description that explicitly covers what it does and when to use it, with concrete natural-language triggers and a distinct niche. Slightly shy of perfect specificity only because a couple of named actions ('URL patterns', 'systematic recovery workflows') are somewhat abstract.

DimensionReasoningScore

Specificity

Names the domain ('Recover deleted GitHub content using the Wayback Machine and Archive.org APIs') plus several concrete actions ('CDX API queries, URL patterns, and systematic recovery workflows' and recovering 'repositories, files, issues, PRs, or wiki pages'); not quite the comprehensive multi-action list of a 5 because 'URL patterns' and 'systematic recovery workflows' are slightly abstract.

4 / 5

Completeness

Explicitly answers both what ('Recover deleted GitHub content using the Wayback Machine and Archive.org APIs ... Covers CDX API queries, URL patterns, and systematic recovery workflows') and when ('Use when repositories, files, issues, PRs, or wiki pages have been deleted from GitHub but may persist in web archives') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural triggers users would say — 'deleted GitHub content', 'repositories, files, issues, PRs, or wiki pages have been deleted', 'web archives'; a few synonyms/extensions omitted (e.g. 'Wayback', 'archived snapshot'), so not a 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche (Wayback/Archive.org recovery of deleted GitHub content) with distinct triggers and minimal overlap with adjacent GitHub skills; the body even delineates complementary skills (github-archive, github-commit-recovery), confirming a non-conflicting niche.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
gadievron/raptor
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.