skill-intent-contract

Use when starting a complex or ambiguous task that risks scope drift

Quality

49%

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 ./skills/skill-intent-contract/SKILL.md

Quality

Content

66%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 a well-sequenced, actionable workflow with strong validation checkpoints, but it suffers from repetition and a monolithic structure that inlines material better split across reference files. Splitting the allocation framework and templates into referenced files would materially improve it.

Suggestions

Move the Step 0 allocation framework (risk table, AUTONOMY_MODE mapping) into a referenced file such as references/allocation.md and link to it, keeping only the decision rule inline.

De-duplicate the intent contract template — keep one canonical template in references/intent-contract-template.md and reference it from Steps 1, 2, and the example.

Remove the 'Benefits' and 'Ready to use!' closing sections, which restate obvious value rather than adding executable guidance.

Dimension	Reasoning	Score
Conciseness	Mostly efficient instruction rather than explanation of known concepts, but the contract template is repeated three times (template, Step 2 heredoc, full example) and the 'Benefits'/'Ready to use!' sections pad without adding actionable guidance.	3 / 5
Actionability	Provides mostly executable guidance — a Write-tool heredoc, an AskUserQuestion block, and a validation report template — though much relies on placeholders like ${USER_GOAL} and [criterion 1] rather than fully concrete commands.	4 / 5
Workflow Clarity	Steps 0–5 are clearly sequenced with explicit validation checkpoints (Step 4 validate against criteria, Step 5 status transitions) and a feedback loop (validate → address gaps → update status), plus a validation checklist.	5 / 5
Progressive Disclosure	A monolithic single file with no bundle files or external references; substantial content that belongs in separate files (the allocation framework, contract template, workflow integrations) is entirely inlined.	2 / 5
	Total	14 / 20 Passed

Description

32%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 gives a trigger condition but omits the skill's actual capabilities, leaving the 'what' entirely unspecified and making it hard to distinguish from other planning skills. It needs a concrete statement of what it does alongside the 'Use when' clause.

Suggestions

Add a concrete 'what' clause naming the skill's actions, e.g. 'Creates a persistent intent contract that captures goals, success criteria, and boundaries, then validates outputs against them.'

Broaden trigger terms with natural synonyms such as 'plan', 'scope creep', 'set goals', or 'define success criteria' instead of relying on the jargon term 'scope drift'.

Tighten distinctiveness by referencing the specific artifact (e.g. '.claude/session-intent.md') so it cannot be confused with generic planning skills.

Dimension	Reasoning	Score
Specificity	The description states only a trigger scenario ("starting a complex or ambiguous task that risks scope drift") without naming any concrete action the skill performs, falling below the midpoint toward the 'no concrete actions' anchor.	2 / 5
Completeness	Only the 'when' is present with no 'what' — the description never says what the skill does, matching the 'only when is present without what' anchor.	2 / 5
Trigger Term Quality	"complex", "ambiguous", and "scope drift" are relevant keywords, but coverage is thin and "scope drift" leans jargon, missing common synonyms users would naturally say.	3 / 5
Distinctiveness Conflict Risk	"complex or ambiguous task that risks scope drift" is very broad and would overlap with most planning or decision-making skills, giving high conflict risk.	2 / 5
	Total	9 / 20 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
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: skills/skill-intent-contract/SKILL.md
Commit: 242e51d

Reviewed: 3 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.