bridge

Use when the user wants hyperflow's behavioral rules to apply outside the terminal CLI — in Claude Code Desktop, claude.ai web, or IDE extensions that don't load CLI plugins. Writes a managed doctrine block into the project's CLAUDE.md so autonomy + intent-routing + commit cadence + role separation + file-first rules carry over. Lossy (no slash commands, no actual skill dispatch) but useful. Trigger with /hyperflow:bridge, "make hyperflow work in desktop", "make hyperflow work in claude.ai", "embed hyperflow doctrine in CLAUDE.md", "portable hyperflow rules".

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/ai-agency/hyperflow/skills/bridge/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.

The body is well-structured and highly actionable with concrete paths, marker formats, and verbatim outputs, plus solid validation in the error-handling table. Its main weakness is conciseness: duplicated output blocks and several overlapping summary sections could be consolidated, and time-sensitive version/date literals are sprinkled inline.

Suggestions

Deduplicate the generate confirmation output — show it once in Subcommand Details and reference it from Examples instead of repeating it verbatim.

Merge the Flow, Instructions, Output, and Overview sections into a single concise summary; they currently restate the same parse-subcommand/write-CLAUDE.md/print-confirmation flow.

Move version literals (4.10.1) and sample timestamps into a clearly marked placeholder or status-output section so time-sensitive values do not bloat the core instructions.

Dimension	Reasoning	Score
Conciseness	Content is substantive and specific but noticeably redundant: the generate confirmation output appears verbatim in both Subcommand Details and Examples, and Flow/Instructions/Output/Overview restate the same summary, while embedded version literals (4.10.1) and timestamps (2026-05-17) are time-sensitive and not isolated in a deprecated section. Not anchor 2 because it avoids generic concept padding, but not 4 due to the duplicated blocks and overlapping summary sections.	3 / 5
Actionability	Gives concrete, executable guidance for an instruction-only skill: exact file paths (./CLAUDE.md, .hyperflow/.bridge-mode), marker strings, numbered per-subcommand steps, and verbatim print outputs. Capped at 4 rather than 5 because the template body is a placeholder and version resolution is described slightly hand-wavily.	4 / 5
Workflow Clarity	Multi-step processes (generate/remove/mode/status) are clearly numbered with the three CLAUDE.md cases handled, and validation exists via the Error Handling table (refuse on malformed markers, refuse on duplicates, idempotent repeated generate). Not 5 because validation lives in a separate table rather than as inline checkpoints in the step sequences.	4 / 5
Progressive Disclosure	Well-organized into clearly labeled sections with one-level-deep external references signaled both inline and in a Resources section (template, DOCTRINE.md, output-style.md). Not 5 because the overlapping Flow/Instructions/Output/Overview sections and the inlined large keep/lose table represent minor organization gaps, and no bundle files exist to verify structure against.	4 / 5
	Total	15 / 20 Passed

Description

82%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 strong: it clearly states what the skill does, when to use it, and supplies concrete trigger phrases in third person. Its only weakness is specificity, as it describes one primary action rather than a comprehensive list of discrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ("Writes a managed doctrine block into the project's CLAUDE.md") plus the carried-over capabilities, but the description centers on essentially one write action rather than enumerating several discrete actions, so it stops at anchor 3 rather than 4.	3 / 5
Completeness	Explicitly answers both what ("Writes a managed doctrine block into the project's CLAUDE.md so ... rules carry over") and when ("Use when the user wants hyperflow's behavioral rules to apply outside the terminal CLI") with concrete trigger phrases, matching the anchor 5 example.	5 / 5
Trigger Term Quality	Provides multiple natural trigger phrasings ("make hyperflow work in desktop", "embed hyperflow doctrine in CLAUDE.md", "portable hyperflow rules") plus the slash command, giving good keyword coverage; not a 5 because the terms are product-specific without synonyms or file extensions.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (hyperflow doctrine portability to non-CLI surfaces) with product-specific distinct triggers, so conflict risk with other skills is minimal.	5 / 5
	Total	17 / 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: 5 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	12 / 16 Passed

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