CtrlK
BlogDocsLog inGet started
Tessl Logo

ralph-two-pass-scan

Cuts GitHub API calls by separating lightweight list scanning from full hydration

57

Quality

66%

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 ./.squad/skills/ralph-two-pass-scan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

87%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 content is highly concise and actionable with executable gh commands and a clear two-pass pattern, and it is well-structured for a simple skill. The only gap is the absence of an explicit validation/feedback checkpoint for the batch scan, which caps workflow clarity.

Suggestions

Add an explicit validation step after Pass 1, e.g. confirm the surviving count and verify skip-rule correctness before hydrating, to introduce a feedback loop.

Document the error-recovery path when more than 30% survive Pass 1 (e.g. "re-tighten filters and re-scan before proceeding") as a concrete retry loop.

Optionally note how to handle `gh` failures or rate limits during hydration so the batch workflow degrades gracefully.

DimensionReasoningScore

Conciseness

The body is lean with no padding and no explanation of concepts Claude already knows; every section (commands, skip table, threshold rule) earns its place. Matches anchor 5.

5 / 5

Actionability

Both `gh issue list` and `gh issue view` commands are copy-paste ready with exact JSON fields, plus a concrete decision table and a quantified 30% hydration rule. Fully executable and covers the common cases.

5 / 5

Workflow Clarity

The two-pass sequence is clear and ordered, but this is a batch operation (scanning up to 100 issues) with no explicit validation/verification checkpoint or error-recovery loop, so the batch-operation cap of 3 applies.

3 / 5

Progressive Disclosure

A single-file, well-organized skill under 50 lines with no external bundle references; per the simple-skills scoring note, that qualifies for a 5.

5 / 5

Total

18

/

20

Passed

Description

46%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 distinctive about its niche but reads as a capability statement rather than trigger guidance, omitting any "Use when..." clause and relying on technical jargon. Strengthening trigger phrasing and adding explicit use-conditions would lift the weaker dimensions.

Suggestions

Add a "Use when..." clause naming concrete triggers, e.g. "Use when triaging GitHub issues in bulk or when Ralph scanning is making too many API calls per round."

Replace or supplement jargon ("hydration") with natural phrases a user would say, such as "fetching issue details" or "reducing GitHub API calls".

List a couple more concrete actions (e.g. "skip owned, blocked, or stale issues") to push specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

Names the domain (GitHub API calls) and two concrete actions ("lightweight list scanning" vs "full hydration"), but the coverage is not comprehensive. Anchor 3 matches; not 4 because it does not list several specific actions.

3 / 5

Completeness

It states a clear "what" (cut API calls by separating scanning from hydration) but gives no "when"/Use-when guidance; the missing trigger clause caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"GitHub API calls" is a partially natural phrase, but "list scanning" and "hydration" are technical jargon with no natural user-facing synonyms or variations. Sits noticeably below the midpoint between anchors 1 and 3.

2 / 5

Distinctiveness Conflict Risk

The niche is specific (GitHub issue two-pass scanning) and unlikely to trigger for unrelated skills, with only minor overlap risk against closely related Ralph/triage skills. Matches anchor 4.

4 / 5

Total

12

/

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
bradygaster/squad
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.