deleting-thoughts

Use when asked to delete, remove, purge, wipe, or "get rid of" an Open Brain thought, or before calling delete_thought (the open-brain-delete-thought connector), which HARD-deletes with no undo. Also use when tempted to delete a thought that is merely outdated or wrong. To edit or deprecate instead of removing, see updating-thoughts.

Quality

85%

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

Quality

Content

81%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 content is a tight, well-structured guide for an irreversible operation, with a clear sequenced workflow and the validation checkpoints the rubric requires for destructive skills. Minor overlap across the cautionary sections and lightly-signalized external references are the only weak spots.

Suggestions

Consolidate the overlapping cautions in 'When to Use', 'This Is Irreversible', 'Red Flags', and 'Rationalizations' to reduce redundancy and tighten token use.

Add a short concrete example of the delete_thought receipt (id + prior content length) so the output step is unambiguous.

If the integrations/delete-thought-mcp README and schemas/thought-audit table are real bundle files, reference them as links; otherwise note they are external environment resources.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence without explaining what a thought or hard-delete is, though the When-to-Use, Irreversible, Red Flags, and Rationalizations sections restate overlapping cautions that could be tightened.	4 / 5
Actionability	Concrete tool names and arguments (search_thoughts/list_thoughts, delete_thought(id), find_derivatives) with an explicit receipt step give mostly executable guidance, but the Red Flags and Rationalizations sections are coaching rather than direct instruction.	4 / 5
Workflow Clarity	A numbered three-step process sequences resolve-id, show-and-confirm, then delete, with explicit validation checkpoints (confirm each id, check derivatives first, pre-check existence) appropriate for this destructive operation.	5 / 5
Progressive Disclosure	A single well-organized file with clear section headers and no bundle to split; external pointers to the integrations README and schemas/thought-audit table are lightly signaled rather than formally referenced.	4 / 5
	Total	17 / 20 Passed

Description

90%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 is well-crafted: it opens with explicit, natural trigger phrases, clearly states the irreversible nature of the action, and distinguishes itself from the related update skill. Its only limitation is that it describes a single concrete action rather than a broad action set.

Dimension	Reasoning	Score
Specificity	Names the Open Brain thought domain and the concrete action of hard-deleting via delete_thought with no undo, but covers a single core action rather than a comprehensive list of specific actions.	3 / 5
Completeness	Explicitly answers both what (hard-delete with no undo) and when, opening with a concrete 'Use when asked to delete...' trigger clause and a second trigger condition.	5 / 5
Trigger Term Quality	Comprehensive natural synonyms are present — 'delete, remove, purge, wipe, or get rid of' — plus the tempted-to-delete 'outdated or wrong' phrasing users would actually say.	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Open Brain thought deletion) with distinct triggers and explicitly redirects edit/deprecate cases to the updating-thoughts skill, minimizing conflict risk.	5 / 5
	Total	18 / 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: NateBJones-Projects/OB1
Path: skills/deleting-thoughts/SKILL.md
Commit: 238df6c

Reviewed: 5 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.