vault-consolidate

Propose or apply consolidation of episodic memories into semantic ones, combining related episodic captures into higher-level semantic summary notes. Use after a long session or when the user asks to clean up, organise, summarise, merge, or declutter memories, or requests memory cleanup or memory management. Always run --propose first so the user can review before --apply commits changes to the vault.

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

86%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 tight, highly actionable skill body: copy-paste commands, a clear propose-review-apply sequence with an explicit human gate, and safety rules for the irreversible apply step. The only gaps are mild repetition of the propose-first rule and the absence of error-recovery guidance for a failed --apply.

Suggestions

Consolidate the propose-before-apply guidance into one place (e.g., keep the Never bullet and the Workflow note, drop the restated rule in Mindset) to trim repeated tokens.

Add a brief recovery note for a partially failed --apply (e.g., re-run is idempotent, or check the audit log) to close the workflow's only validation gap.

Dimension	Reasoning	Score
Conciseness	The body is lean and operational with no re-explanation of known concepts, but the propose-before-apply rule is stated three times ("Think of `--propose` as generating a diff", "Always propose before applying", and Never bullet #1) and the no-deletion guarantee appears in both "Important" and Never #3 — minor trimming possible. Not anchor 5's "every token earns its place", but well above the verbose anchors.	4 / 5
Actionability	Fully executable, copy-paste-ready commands (`vault-cli consolidate --propose [--project <id>]`, `vault-cli consolidate --apply`), a concrete review file path (`00-inbox/consolidation-proposals.md`), and a specific expected output string ("No episodic memories found to consolidate") with the action to take — covering the common cases including the empty-vault edge case.	5 / 5
Workflow Clarity	A clear 3-step sequence with an explicit human-review validation checkpoint (Step 2: set status approved or rejected) and an explicit pause-and-confirm rule, plus handling of the empty-output case. The destructive/batch cap at 3 does not apply because validation is present; it stays at 4 rather than 5 because there is no error-recovery guidance if `--apply` itself fails partway.	4 / 5
Progressive Disclosure	A ~54-line single-purpose skill with well-organized sections and no need for external references: no bundle files exist (references/, scripts/, assets/ are absent) and the only path mentioned is a vault file, not a bundle reference. Per the simple-skill note, well-organized sections alone earn the top score here.	5 / 5
	Total	18 / 20 Passed

Description

83%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 strong description that explicitly states what the skill does and when to use it, with natural trigger terms and a distinctive episodic-to-semantic consolidation niche. Minor improvements are possible: add "consolidate" to the trigger list and slightly narrow the broad "memory management" phrasing.

Dimension	Reasoning	Score
Specificity	Names concrete actions — "Propose or apply consolidation", "combining related episodic captures into higher-level semantic summary notes", and the concrete --propose/--apply distinction — with only minor gaps (apply-side effects like marking sources superseded are not mentioned). It lists several specific actions rather than only 1-2, so it sits above anchor 3 but below the comprehensive coverage of anchor 5.	4 / 5
Completeness	Clearly and explicitly answers both questions: what ("Propose or apply consolidation of episodic memories into semantic ones, combining related episodic captures into higher-level semantic summary notes") and when ("Use after a long session or when the user asks to clean up, organise, summarise, merge, or declutter memories..."), with concrete trigger phrases — a direct match to the anchor-5 exemplar.	5 / 5
Trigger Term Quality	Good natural-term coverage: "clean up, organise, summarise, merge, or declutter memories, or requests memory cleanup or memory management" plus "Use after a long session". A few natural terms are missing — notably "consolidate" (the skill's own verb, absent from the trigger list) and variations like "tidy" — so it does not reach anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	A clear niche (episodic-to-semantic memory consolidation in a vault) with domain-specific triggers, so mostly distinct with only minor overlap risk. The phrase "memory cleanup or memory management" is broad enough to collide with generic memory-maintenance skills, keeping it below anchor 5.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: pantheon-org/tekhne
Path: skills/agentic-harness/vault-consolidate/SKILL.md
Commit: a1083f4

Reviewed: 2 hours 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.