confirm-action

Ask the user to confirm before taking a significant action. Use before containment, remediation, or other impactful operations to ensure analyst approval. Presents options and waits for response.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/confirm-action/SKILL.md

Quality

Content

67%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.

A well-organized, concise body for a simple confirmation-gating skill with clear inputs, workflow, and illustrative examples. The main weakness is actionability: workflow steps describe intent without specifying the concrete mechanism for presenting, collecting, and returning the response.

Suggestions

Specify the concrete mechanism for each workflow step, e.g., the exact tool call or return format used to present options, capture the user's selection, and hand USER_RESPONSE back to the calling workflow.

Add a brief validation note in Step 2 for handling responses outside the predefined RESPONSE_OPTIONS (e.g., map unknown input to a default or re-prompt), giving the wait/return loop an explicit checkpoint.

Tighten the three example blocks into one parameterized template plus a compact table of scenario-specific option sets to reduce structural repetition.

Dimension	Reasoning	Score
Conciseness	Lean body with no over-explanation of known concepts; the three example blocks are structurally similar but each illustrates a distinct option set, leaving only minor trim potential, fitting the 4 anchor.	4 / 5
Actionability	Concrete example question/option pairs anchor the guidance, but steps like "Collect the user's selection or custom input" and "Provide the response back... for decision branching" describe intent rather than specifying mechanism, matching the 3 anchor's incomplete concrete guidance.	3 / 5
Workflow Clarity	A clear unambiguous 3-step sequence (Present → Wait → Return) for a simple gating skill; the destructive-operation cap does not bind since the skill gates rather than performs those ops, but no validation of the returned response keeps it at 4 rather than 5.	4 / 5
Progressive Disclosure	No bundle files exist and all content is inline in well-organized sections (Inputs, Workflow, Outputs, When to Use, Examples); at ~68 lines it slightly exceeds the 50-line simple-skill threshold, placing it at 4 rather than 5.	4 / 5
	Total	15 / 20 Passed

Description

78%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.

A concise, well-targeted description that clearly states both capability and trigger conditions in third person. It is strong on completeness and trigger quality, with only minor room to add action synonyms and more granular action enumeration.

Dimension	Reasoning	Score
Specificity	Names the confirmation-gating domain plus 1-2 concrete actions ("Ask the user to confirm", "Presents options and waits for response"), but does not enumerate several specific actions, matching the 3 anchor and falling below the 4 anchor's 'several specific actions'.	3 / 5
Completeness	Explicitly answers both what (ask/present/wait) and when via an explicit "Use before containment, remediation, or other impactful operations" trigger clause with concrete triggers, matching the 5 anchor.	5 / 5
Trigger Term Quality	Good natural SOC keywords ("confirm", "containment", "remediation", "analyst approval") a user would say, but missing common synonyms like "approve" or "proceed", so it sits at 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to security-operations gating with distinct triggers (containment, remediation, analyst approval), giving a clear niche with only minor overlap risk against generic confirmation skills, fitting the 4 anchor better than 3 or 5.	4 / 5
	Total	16 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: dandye/ai-runbooks
Path: skills/confirm-action/SKILL.md
Commit: 72a6863

Reviewed: 6 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.