context-anchored-fallback-report

Generate documents with write_file when retrieval tools fail, with explicit guardrails against task context drift

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/write-file-fallback-report-enhanced-4bc5c2/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear sequenced workflow and validation checklist, but it is heavily padded with redundant restatements of the same guidance and keeps all content inline in one long monolithic file.

Suggestions

Collapse the redundant restatements (decision tree, red/green flags, best-practices, pitfalls, success criteria, quick-reference card) into a single concise checklist — the same rule is repeated ~6 times.

Move the full Python code example and the quick-reference card into separate reference files (e.g., references/quick-reference.md) and link to them one level deep to improve progressive disclosure.

Trim the verbose CONTEXT_DRIFT_WARNING and FALLBACK_TRIGGERS blocks, which restate guidance already covered in the step-by-step section.

Dimension	Reasoning	Score
Conciseness	The guidance avoids explaining basic concepts, but the same message (anchor to context, pivot after 2 failures, generate with write_file) is restated across the decision tree, red/green flags, best-practices, pitfalls, success criteria, and quick-reference card, inflating a ~50-line idea into ~300 lines.	2 / 3
Actionability	It provides concrete thresholds (2+ failures), a copy-paste-ready markdown document template, an explicit write_file execution pattern, and a list_dir verification step — specific and immediately usable.	3 / 3
Workflow Clarity	Steps 0–5 are clearly sequenced with an explicit context anchor up front, a verification checkpoint in Step 4, and a completion checklist in Step 5 that serves as a validation gate.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a single ~300-line monolith with good section organization but no file references; content that could be split out (the full code example, quick-reference card) is all inline rather than one level deep.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 names a concrete tool and a distinct niche, but relies on internal jargon for its trigger terms and omits an explicit 'Use when...' user-facing clause, capping completeness and trigger quality at the mid level.

Suggestions

Add an explicit 'Use when...' clause framed in user-facing language (e.g., 'Use when web search or data retrieval tools fail during report generation').

Replace internal jargon ('retrieval tools', 'task context drift') with natural terms users would say ('web search unavailable', 'tools down', 'generate the report anyway').

List a second concrete action to lift specificity (e.g., 'generate documents with write_file, verify output against the original request').

Dimension	Reasoning	Score
Specificity	Names a concrete tool (write_file) and one core action (generate documents) plus a guardrail feature, but it lists a single main action rather than the multiple concrete actions the top anchor requires.	2 / 3
Completeness	It states what the skill does and embeds a 'when retrieval tools fail' trigger, but lacks an explicit 'Use when...' clause and the trigger is an internal tool-failure state rather than a user-facing situation, so per the guideline it caps at 2.	2 / 3
Trigger Term Quality	It includes semi-natural terms like 'documents' and 'tools fail', but leans heavily on internal jargon ('retrieval tools', 'write_file', 'task context drift') that a user would not naturally say.	2 / 3
Distinctiveness Conflict Risk	The fallback-on-tool-failure-with-context-drift-guardrails niche is highly specific and unlikely to be confused with or triggered by other skills.	3 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/write-file-fallback-report-enhanced-4bc5c2/SKILL.md
Commit: c5a9c4b

Reviewed: 2 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.