cache

Use when the user wants to view, search, add, edit, prune, archive, or clear hyperflow memory entries. CRUD interface for `.hyperflow/memory/` — never modifies source code, only memory files. Trigger with /hyperflow:cache, "show memory", "search memory for X", "clear memory", "what does hyperflow remember about Y".

Quality

83%

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

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 operational skill with concrete templates, a thorough error-handling table, and validation on destructive operations. It loses points for redundant overview/flow/instructions sections and two broken references — the DOCTRINE.md link path and the missing scripts/memory-index.py — which hurt both actionability and navigation.

Suggestions

Collapse the `Flow`, `Instructions`, and `Overview` sections into a single lifecycle description to remove the duplicated 4-step parse/validate/execute/print list and the repeated subcommand enumeration.

Fix the DOCTRINE.md reference: change `[DOCTRINE.md](../hyperflow/DOCTRINE.md)` to `[DOCTRINE.md](references/DOCTRINE.md)` so the link resolves to the bundled file.

Resolve the `scripts/memory-index.py` reference — either add the script to a `scripts/` directory or reword the `add` section so it does not instruct running a script that is not shipped with the skill.

Dimension	Reasoning	Score
Conciseness	Largely efficient (terse tables, no concept padding), but the `Flow`, `Instructions`, and `Overview` sections redundantly restate the same parse→validate→execute→print lifecycle and re-list subcommands already in the table — noticeable duplication beyond 'minor'. Confirmed below 4 because whole duplicated sections, not just trimmable phrases; confirmed above 2 because the bulk is tight, not padded with explanations Claude already knows.	3 / 5
Actionability	Concrete and mostly executable: the `add` entry template (`### [YYYY-MM-DD] <title>` with What/Why/Evidence), `grep/ripgrep` commands, exact archive paths, and the 8-step compact flow are copy-paste ready. Confirmed below 5 because `scripts/memory-index.py` is referenced as `python3 scripts/memory-index.py .hyperflow` but no `scripts/` directory exists, so that instruction cannot run as written; confirmed above 3 because the guidance is real commands/templates, not pseudocode.	4 / 5
Workflow Clarity	Destructive/batch ops carry validation: `clear` requires AskUserQuestion confirmation and backs up to `cleared-<timestamp>.md`; `prune` uses `test -f` before removal; `compact` has a Dedup Reviewer plus checksum refresh; the Error Handling table gives recovery behaviors. Confirmed below 5 because the top-level `Flow` is a generic 4-step list ('execute subcommand') whose detail lives elsewhere; confirmed above 3 because validation checkpoints are present, so the destructive-cap-at-3 rule does not apply.	4 / 5
Progressive Disclosure	SKILL.md acts as an overview with one-level-deep references to real files (`references/memory-system.md`, `references/compaction.md`, `references/output-style.md`) and a Resources section with descriptions. Confirmed below 5 because navigation is impaired by two broken references: `[DOCTRINE.md](../hyperflow/DOCTRINE.md)` points to a non-existent path (the file is at `references/DOCTRINE.md`) and `scripts/memory-index.py` has no corresponding directory; confirmed above 3 because most references resolve and structure is genuinely one-level-deep.	4 / 5
	Total	15 / 20 Passed

Description

100%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: concrete multi-action capability list, natural and varied trigger phrases, explicit what-and-when, and a tightly scoped niche that avoids conflict. The only nit is the second-person 'Use when the user wants to' framing, but it matches the rubric's own good-example convention and is not the penalized 'You can use this' form.

Dimension	Reasoning	Score
Specificity	Lists seven concrete CRUD actions ("view, search, add, edit, prune, archive, or clear hyperflow memory entries") plus a precise interface target ("CRUD interface for `.hyperflow/memory/`") — comprehensive, not vague. Confirmed above 4 because the action list is multi-action and exhaustive, not 'several with minor gaps'.	5 / 5
Completeness	Explicitly answers both 'what' (CRUD interface over .hyperflow/memory/, never modifies source) and 'when' ("Use when the user wants to..." + "Trigger with...") with concrete trigger phrases. Confirmed above 4 because 'when' is explicit and specific, not merely present.	5 / 5
Trigger Term Quality	Provides natural user phrases — "show memory", "search memory for X", "clear memory", "what does hyperflow remember about Y" — plus the slash trigger `/hyperflow:cache`, covering synonyms and realistic phrasings. Confirmed above 4 because it includes varied natural synonyms rather than 'a few natural terms missing'.	5 / 5
Distinctiveness Conflict Risk	Scoped to "hyperflow memory entries" / ".hyperflow/memory/" / "/hyperflow:cache" — a clear niche with distinct triggers and minimal conflict risk with unrelated skills. Confirmed above 4: the namespace qualifier makes overlap with generic skills very unlikely.	5 / 5
	Total	20 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	12 / 16 Passed

Repository: jeremylongshore/tons-of-skills-marketplace
Path: plugins/ai-agency/hyperflow/skills/cache/SKILL.md
Commit: 88dcf65

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.