intake-audit

Use when a quest does not start from a blank state and the agent must first audit, trust-rank, and reconcile existing baselines, results, drafts, or review materials before choosing the next anchor.

Quality

77%

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 ./src/skills/intake-audit/SKILL.md

Quality

Content

70%

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

The body is a well-structured, actionable intake workflow with clear sequencing, validation checkpoints, and a real one-level-deep template reference. Its weakest dimensions are conciseness (repetition across sections) and actionability (artifact calls stubbed with ellipses rather than complete signatures).

Suggestions

Collapse the overlapping Purpose / Use when / Do not use when sections so each trigger and rule is stated once, trimming roughly 30–50 lines.

Replace the "..." placeholders in artifact calls with minimal concrete argument lists (or one fully-worked example call) so the guidance is copy-paste ready.

Consider moving the full classification taxonomies (intake states, trust levels, manuscript-visibility buckets) into the state-audit template reference to slim the main body.

Dimension	Reasoning	Score
Conciseness	The body is ~320 lines with repetition across Purpose, Use when, and Do not use when, and could be tightened; it avoids explaining concepts Claude already knows but does not earn a 3 because several sections restate the same intent.	2 / 3
Actionability	It names concrete tool calls and parameters (e.g. memory.list_recent(scope='quest', limit=5), artifact.attach_baseline(...), bash_exec(...)), but most artifact calls are stubbed with "..." ellipses, so guidance is concrete yet incomplete rather than copy-paste ready. Not a 1 because specific methods and fields are given; not a 3 because key call arguments are missing.	2 / 3
Workflow Clarity	A clearly numbered 1–7 workflow with explicit validation checkpoints (trust-rank/reconcile in step 4, "If the evidence is insufficient... record that insufficiency explicitly") and non-negotiable guardrails. Not a 2 because checkpoints are explicit, not implicit.	3 / 3
Progressive Disclosure	Sections are well-organized with clear navigation, and the one referenced bundle file references/state-audit-template.md exists and is signaled one level deep. Not a 2 because the reference is clearly signaled and the structure supports easy navigation rather than a monolithic wall.	3 / 3
	Total	10 / 12 Passed

Description

85%

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, complete, and clearly scoped, with third-person voice and an explicit Use-when trigger. Its main weakness is trigger-term quality: the language is framework jargon ("quest", "anchor", "trust-rank") rather than natural user phrasing.

Suggestions

Add natural trigger phrasing users would actually say, e.g. "Use when the user says the baseline already exists, asks not to rerun from scratch, or wants to organize existing results before continuing."

Soften jargon like "trust-rank" and "anchor" with plain-language equivalents so the trigger reads naturally to a non-framework user.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "audit, trust-rank, and reconcile existing baselines, results, drafts, or review materials" — matching the anchor for listing several specific concrete actions; not below because it is not merely naming a domain.	3 / 3
Completeness	An explicit "Use when..." clause states when to invoke it and the verb list states what it does, answering both what and when. Not a 2 because the when is explicit, not merely implied.	3 / 3
Trigger Term Quality	The trigger "a quest does not start from a blank state" and terms like "trust-rank" and "anchor" are domain jargon rather than phrases a user would naturally say; relevant but missing common variations such as "baseline already exists" or "don't rerun from scratch". Not a 3 because natural-language coverage is thin.	2 / 3
Distinctiveness Conflict Risk	The intake-audit niche (normalizing pre-existing research state before routing) is distinct and unlikely to trigger for the wrong skill. Not a 2 because it is not a generic overlap candidate.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: ResearAI/DeepScientist
Path: src/skills/intake-audit/SKILL.md
Commit: b366244

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.