CtrlK
BlogDocsLog inGet started
Tessl Logo

search-fail-pivot

Heuristic for detecting search tool failures and pivoting to domain knowledge for document generation

50

Quality

63%

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 ./benchmarks/gdpval/skills/search-fail-pivot/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 well-structured with a clear heuristic, sequenced steps, and a useful decision flow, but it is held back by partial code examples and some redundant restating of the core rule in the Benefits and Anti-Patterns sections. It is a solid, mostly actionable skill with minor tightening needed.

Suggestions

Replace the truncated reportlab snippet (ending in '# ... continue') with a complete, runnable example or explicitly justify why it is intentionally partial.

Collapse the Benefits and Anti-Patterns sections into the core heuristic to remove restatement and recover tokens.

Add a brief verification step after document generation (e.g. confirm the output file exists and is non-empty) to close the workflow-clarity validation gap.

DimensionReasoningScore

Conciseness

Mostly efficient with a clear heuristic up front, but the Benefits and Anti-Patterns sections largely restate the 2-failure rule, and the 2-retry limit is repeated multiple times, so it could be tightened.

3 / 5

Actionability

The 2-failure rule and pivot steps are concrete, but the code examples are partial — the reportlab snippet ends with '# ... continue with known information' and the known_facts dict is illustrative rather than complete executable code, leaving key details missing.

3 / 5

Workflow Clarity

Steps 1-4 are clearly sequenced and the Example Decision Flow provides explicit branching checkpoints (retry on failure #1, pivot on failure #2+); the only minor gap is no validation of the generated document, and the destructive/batch cap does not apply here.

4 / 5

Progressive Disclosure

Well-organized with clearly labeled sections and a self-contained heuristic requiring no external references; it is over 50 lines, so the simple-skill exception to reach 5 does not apply, but structure is good.

4 / 5

Total

14

/

20

Passed

Description

50%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 clearly states what the skill does but omits any explicit 'when to use it' trigger guidance, which limits completeness and trigger-term quality. It is reasonably specific and distinct but would benefit from a 'Use when...' clause with natural user phrases.

Suggestions

Add a 'Use when...' clause with natural trigger phrases, e.g. 'Use when search_web repeatedly fails with unknown errors or empty results during document generation tasks.'

Include common user-facing synonyms such as 'search not working', 'search returning errors', or 'search unavailable' to improve trigger-term coverage.

Tighten the action list to concrete verbs ('detect', 'count', 'pivot', 'generate') to lift specificity above the 1-2 action range.

DimensionReasoningScore

Specificity

Names the domain ('search tool failures') and two concrete actions — 'detecting search tool failures' and 'pivoting to domain knowledge for document generation' — but coverage is not comprehensive, matching the 1-2 concrete actions anchor.

3 / 5

Completeness

Provides a clear 'what' (detect failures and pivot) but no explicit 'Use when...' trigger clause, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Contains relevant keywords ('search tool failures', 'domain knowledge', 'document generation') but misses common natural variations a user might say (e.g. 'search not working', 'search broken'), so it sits at the some-relevant-keywords anchor rather than above.

3 / 5

Distinctiveness Conflict Risk

Targets a fairly specific niche (search-tool failure → domain-knowledge pivot) but could still overlap with general retry/error-handling heuristics, fitting the somewhat-specific-but-could-overlap anchor.

3 / 5

Total

12

/

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
HKUDS/OpenSpace
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.