CtrlK
BlogDocsLog inGet started
Tessl Logo

sitemap-task-bias

Use when creating or auditing an agent-team sitemap, Task Bias ledger, concept coverage, product surface map, validation chain, or missing-concept check.

66

Quality

78%

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 ./.agents/skills/sitemap-task-bias/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The body is token-efficient and well-structured for a simple audit skill, but its central instruction (producing task biases) is vague and the workflow lacks an explicit coverage-verification checkpoint. Both gaps keep it from the top band on actionability and workflow clarity.

Suggestions

Define 'task bias' concretely in step 3 with a one-line example of a well-formed bias so Claude knows exactly what to produce.

Add an explicit validation checkpoint, e.g., 'Before returning, verify every required concept from step 2 is either covered or recorded as missing in the ledger.'

Show the expected shape of an output record (covered/missing/task_biases/evidence_files) with a brief example so the Output contract is unambiguous.

DimensionReasoningScore

Conciseness

The body is lean with no padding or explanation of concepts Claude already knows — each of the four steps and the Output section carries actionable information, matching the 'every token earns its place' anchor.

3 / 3

Actionability

Steps 1, 2, and 4 and the Output section give concrete lists, a specific ledger path, and named output fields, but step 3 ('Add task biases that protect the build from dropping important concerns') leaves the core action under-specified without defining what a task bias is or how to formulate one, fitting 'some concrete guidance but incomplete'.

2 / 3

Workflow Clarity

The four steps are clearly sequenced, but there is no explicit validation or verification checkpoint (e.g., confirming all required concepts are covered before finalizing), so it sits at 'steps listed but validation gaps' rather than the checkpoint-driven anchor at 3.

2 / 3

Progressive Disclosure

At roughly 16 lines with well-organized Procedure and Output sections and no need for external references, this qualifies for the simple-skill allowance that progressive disclosure can score 3 on organization alone.

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 concise, explicit about both purpose and trigger conditions, and highly distinctive within its niche. Its main weakness is jargon-heavy trigger terms that lack common user-facing variations.

Suggestions

Add plain-language synonyms or common phrasings alongside the jargon (e.g., 'agent-team sitemap (team structure / responsibility map)') so users who don't know the internal terminology can still trigger it.

DimensionReasoningScore

Specificity

Lists multiple concrete artifacts the skill creates or audits — 'agent-team sitemap, Task Bias ledger, concept coverage, product surface map, validation chain, or missing-concept check' — matching the 'lists multiple specific concrete actions' anchor rather than the partial domain-only anchor at 2.

3 / 3

Completeness

The 'Use when creating or auditing...' clause explicitly answers both what the skill does and when to use it, satisfying the explicit-trigger requirement; it is not capped at 2 because an explicit 'Use when' trigger is present.

3 / 3

Trigger Term Quality

Keywords like 'Task Bias ledger' and 'validation chain' are relevant to the domain but are specialized jargon with no common variations or synonyms, fitting 'some relevant keywords but missing common variations' and falling short of the natural-variation coverage at 3.

2 / 3

Distinctiveness Conflict Risk

Highly niche triggers such as 'agent-team sitemap' and 'Task Bias ledger' carve a clear, specialized niche that is unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

11

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
agentlas-ai/Agentlas-OS
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.