flush

Use when the user wants to manually flush a deferred-commit queue from a prior or interrupted chain. Reads .hyperflow/commits-queue/manifest.json, fast-forwards the staging branch onto the user's branch, deletes staging, clears the queue. Recovery interface when a chain crashed before its Step 4 auto-flush ran. Trigger with /hyperflow:flush, "flush pending commits", "flush queue", "apply staged commits", "where are my commits".

Quality

80%

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

61%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 actionable and well-structured with concrete commands and good error handling, but it repeats itself between the intro and Overview and lacks a post-flush verification step for a destructive operation. Tightening the redundancy and adding a verification checkpoint would lift it clearly above the midpoint.

Suggestions

Collapse the 'Overview' section into the intro paragraph — both explain that the skill handles interrupted-chain recovery, so the duplication is pure token cost.

Add an explicit post-flush verification step to the Flow (e.g. confirm the queued commits now appear on the user's branch via git log) to satisfy the destructive-operation validation requirement and lift workflow_clarity above 3.

Merge the Subcommands table content into the Flow or keep only one of the two, since the (no arg)/--dry-run rows restate steps already covered elsewhere.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of generic-concept padding, but the 'Overview' section restates the intro paragraph ('this skill exists for recovery... crashed before wrap-up') and the Subcommands table overlaps the Flow, so it could be tightened.	3 / 5
Actionability	Provides concrete, executable commands — 'bash $PLUGIN_ROOT/scripts/flush-commits.sh $PROJECT_ROOT [--dry-run]', 'git rebase hyperflow/staging-<chain-id>', 'git cherry-pick <staging-base>.....' — plus example output; the only gap is reliance on an external script for the core mechanism.	4 / 5
Workflow Clarity	Sequencing and an error-handling table are present with a manifest-existence pre-check, but this is a destructive/batch operation (replays N commits, deletes the staging branch) with no post-flush verification step, which caps the score at 3 per the rubric.	3 / 5
Progressive Disclosure	Well-organized into clearly labeled sections with one-level-deep, clearly signaled references (flush-commits.sh, queue-commit.sh, DOCTRINE.md Layer 8); no bundle dirs exist alongside the skill, and the body is a single appropriately-scoped file with minor organization overlap.	4 / 5
	Total	14 / 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.

The description is specific, complete, and well-triggered: it names concrete actions, gives explicit 'Use when' guidance with natural trigger phrases, and occupies a distinct niche. It is one of the stronger descriptions in the reference set.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Reads .hyperflow/commits-queue/manifest.json, fast-forwards the staging branch onto the user's branch, deletes staging, clears the queue' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly states both what ('fast-forwards... deletes staging, clears the queue') and when ('Use when the user wants to manually flush... interrupted chain', 'Recovery interface when a chain crashed before its Step 4 auto-flush ran') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say — 'flush pending commits', 'flush queue', 'apply staged commits', 'where are my commits' — plus the slash handle, covering synonyms and a casual variant.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (deferred-commit queue flush / recovery) with distinctive triggers unlikely to fire for unrelated skills; uses third-person voice throughout with no conflict-prone generic language.	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: 3 suspicious	Warning
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	12 / 16 Passed

Repository: jeremylongshore/tons-of-skills-marketplace
Path: plugins/ai-agency/hyperflow/skills/flush/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.