fledgeling-co/fledgeling-plugins

SWE Skills from Fledgeling: thirty-six Claude Code plugins for building and shipping software with agents. Each carries its own README, an eval suite or a stated reason it has none, and an icon on the family silhouette from the same measured design pipeline.

2Stars on the repository
55Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

agent-voice

01

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of agent-voice

Give agent-authored text a real voice: the prose an agent emits inside Claude Code and other harnesses. Routes to one of seven registers — terminal reply, work report, commit and PR, review comment, written document, SKILL.md and instruction file, subagent brief — then drafts or revises against evidence-anchored rules…

not rated 2 3d ago A 257 tokens original MIT

anvil-errand

02

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of anvil-errand

Send a Claude Code agent to work in a container on another machine through Anvil, using the single anvil errand verb, and read its refusals correctly when a piece of the path is missing. Covers the whole loop — check the preconditions, start the errand, watch it, stop it — and translates each stable refusal kind…

not rated 2 3d ago A 232 tokens original MIT

atlas-publish

03

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of atlas-publish

Atlas/Bella release conductor — take the open PRs to a registered draft release, on the OTA lane or the App Store lane. Use when someone wants Atlas work in front of users: "ship an Atlas release", "publish an OTA update", "release the app", "cut a new Atlas build", "push a JS-only update to users", "do a full App…

not rated 2 3d ago A 280 tokens original MIT

be-my-witness

04

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of be-my-witness

Validate a UI screenshot against what a test expected and against a design mock, and return both a pass/fail gate and severity-ranked findings. Use whenever a test, capture suite, or review step has produced a screenshot that something now has to judge — "does this screenshot match the expected output", "does the…

not rated 2 3d ago A 155 tokens original MIT

better-goal

05

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of better-goal

Hold a long autonomous run to a finish line using a Stop guard and a stall watcher this skill creates itself, with no dependence on the /goal command. Use when someone wants a run that keeps going until the work is actually done — "set a goal to ship the rest of the backlog", "keep going until every item is complete"…

not rated 2 3d ago A 357 tokens original MIT

better-loop

06

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of better-loop

Arm recurring or event-driven work as a change-gated watcher this skill creates itself, so a tick fires only when something has actually changed. Use when someone wants work that keeps running — "loop on this", "keep checking the deploy", "monitor the benchmark runs and fix errors", "create a loop prompt", "harden…

not rated 2 3d ago A 298 tokens original MIT

braindump

07

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Write a context-compaction summary that survives being the only thing the next session has, and prove it against the transcript it replaced and against Claude Code's own /compact. Use this whenever someone is about to run /compact, asks what to keep before compacting, wants to hand a long session off to a fresh one…

not rated 2 3d ago A 168 tokens original MIT

clarify

08

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of clarify

Decide whether to interrupt the user with a question, then ask it so it takes one click to answer. Use this whenever you are about to ask the user something mid-task, when you hit a fork with several defensible answers, when a request is ambiguous enough that two readings would produce different work, before anything…

not rated 2 3d ago A 307 tokens original MIT

code-review

09

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of code-review

Review a diff, a PR, or a branch range and report findings — correctness bugs first, then reuse, simplification, efficiency, altitude and convention breaches. Use when the user asks for a code review, asks to "review my changes / PR / diff / branch", asks for a security, performance, dead-code, test-coverage…

not rated 2 3d ago B 349 tokens original MIT

create-luke-content

10

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of create-luke-content

Write any content in Luke Rhodes' authentic voice (Diolog CTO and co-founder), routed through the right persona variant: LinkedIn posts and long-form blog articles, marketing content (announcements, release notes, launch/landing copy, campaign emails), code reviews, Slack/chat messages, short-form content (tweets/X…

not rated 2 3d ago A 232 tokens original MIT

create-luke-content

11

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of create-luke-content

Write any content in Luke Rhodes' authentic voice (Diolog CTO and co-founder), routed through the right persona variant: LinkedIn posts and long-form blog articles (with graphic concept), marketing content (announcements, release notes, landing copy, campaign emails), code reviews, Slack/chat messages, short-form…

not rated 2 3d ago A 228 tokens original MIT

create-mac-icon

12

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of create-mac-icon

Create a macOS app icon end-to-end — direction chosen from a 532-icon corpus catalogue, subject-mined glyph, three generation engines (hand-authored layered SVG, Arrow vector, corpus-referenced raster), a written audit.html contact sheet, and a measured fidelity loop that iterates the SVG master against the winning…

not rated 2 3d ago A 158 tokens original MIT

create-skill

13

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of create-skill

End-to-end pipeline for building a brand-new skill from scratch, when there is no predecessor to improve. Starts with a broad clarifying interview so the desired outcome is actually pinned down (recommendations offered, notes allowed per answer, multi-choice where it fits, and nothing asked that is already answered…

not rated 2 3d ago A 235 tokens original MIT

create-swe-project

14

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of create-swe-project

Scaffold a complete, working new project in /Dev from a project idea — the slipway is where new ships are launched. Use this whenever the user wants to start a new project, app, product, or prototype — "new project", "set up a project", "scaffold X", "spin up an app for…", "start building ", "greenfield", "I have an…

not rated 2 3d ago B 355 tokens original MIT

deck-craft

15

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of deck-craft

Build, review, or convert any slide deck — self-contained HTML presentations, lecturn.deck/1 JSON (and .pptx through it), or Diolog investor decks assembled from a bundled library of 200 slide layouts in 27 families. Use whenever the user wants a deck, presentation, slides, pitch, keynote, investor update, board pack…

not rated 2 3d ago A 229 tokens original MIT

defer

16

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of defer

Decide which model a piece of work goes to, and produce the exact command that sends it there. One routing policy for every skill that hands work outside the session: six task classes mapped to ten lanes across five model families, each pinned to a model and an effort, with the CLI arguments, the environment GLM…

not rated 2 3d ago A 254 tokens original MIT

design-craft

17

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of design-craft

Use whenever the user asks to design or build a user-facing visual artifact — a landing page, app screen, dashboard, clickable prototype, native iOS/Android mockups, wireframe, design variations, a tweakable panel, a motion piece or scroll-driven marketing page, a 3D/WebGL hero, a print document, generated imagery, or…

not rated 2 3d ago A 361 tokens original MIT

design-review

18

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of design-review

Expert design and UX review of rendered web apps, websites, app UI flows, infographics, and design artifacts — the last pass before a human looks at AI-built UI. Runs deterministic accessibility, performance, contrast, motion and layout-integrity gates, then structural, state, component-inventory, craft, flow…

not rated 2 3d ago A 318 tokens original MIT

discipline

19

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of discipline

Session-start operating defaults that cut token spend without cutting task success, tuned for Claude Opus 5 agentic coding. Ships a byte-stable block for the cached system prefix (Perch proxy, CLAUDE.md, or an output style) plus the evidence behind every clause. Use when someone asks to reduce token usage, stop…

not rated 2 3d ago A 140 tokens original MIT

dossier-report

20

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of dossier-report

Turn a research question into one published, uniquely-themed HTML report page — a Dossier paid+free deep-research panel read in full, compiled into a claim graph, then designed from scratch around its own subject and written out to /Dev/dossier/ /index.html for .fledgeling.app. Ships three readings of the same…

not rated 2 3d ago A 485 tokens original MIT

eli5

21

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of eli5

Build an interactive, self-contained HTML explainer that makes a hard idea genuinely click — a thing you operate, not a document you read. Lets the mechanism pick the shape of the page from eight that recur (Machine, Field, Solid, Ladder, Fork, Trace, Assembly, Reveal) rather than giving every topic the same tabs, and…

not rated 2 3d ago A 320 tokens original MIT

email-digest

22

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of email-digest

Build a recurring multi-item digest or roundup email that survives contact with real inboxes - a tiered layout that absorbs volume instead of capping it, a table-based render that works in Outlook's Word engine and with images blocked, and a deterministic gate carrying every rule back to the evidence behind it. Use…

not rated 2 3d ago A 217 tokens original MIT

flagship

23

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of flagship

Conduct many concurrent Claude Code sessions as one portfolio — the layer above ship-armada, for when the work is already spread across a dozen live sessions rather than waiting in one repo's backlog. Use when someone says run the armada across my open sessions, coordinate all these sessions, keep each one ticking…

not rated 2 3d ago A 299 tokens original MIT

geminify

24

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Part of geminify

Add a Gemini-calibrated gemini.md to an existing skill, so the same skill works on Google's models as well as Claude's. Reads the target skill, scans it for the unbounded scopes and assumed verification that Gemini handles differently, assembles the file from a shared core plus only the modules the skill's own subject…

not rated 2 3d ago A 215 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: