Owner

obra

10 indexed repositories · View on GitHub

superpowers
An agentic skills framework & software development methodology that works.

Shell · 288621 stars
superpowers-marketplace
Curated Claude Code plugin marketplace

1264 stars
the-elements-of-style
William Strunk Jr.'s Elements of Style (1918) in markdown format for AI agents

HTML · 579 stars
episodic-memory

TypeScript · 478 stars
private-journal-mcp
A lightweight MCP server that provides Claude with a private journaling capability to process feelings and thoughts

TypeScript · 449 stars
superpowers-chrome
Claude Code plugin for direct Chrome browser control via DevTools Protocol - zero dependencies

JavaScript · 354 stars
dotfiles

Shell · 114 stars
lace
Lightweight agentic coding environment

TypeScript · 52 stars
winpepper
Windows-native local dictation. Hold a hotkey, speak, release — cleaned-up words appear in the focused app. Parakeet TDT v3 ASR + LlamaSh...

C# · 18 stars
narcolepsyd
Idle power optimizer for Linux laptops with Intel hybrid CPUs

Rust · 13 stars

Beginner friendly Everything

Open All

Workflow has first-class specs/plans but no durable QA/acceptance artifact layer Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

obra/superpowers#2332 · 4 comments · Opened Sep 18, 2026
finishing-a-development-branch: PR review has no lifecycle transition back to merge/release Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

obra/superpowers#2316 · 2 comments · Opened Sep 17, 2026
writing-plans: discover and reuse available QA tools before inventing bespoke verification Open

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

obra/superpowers#2314 · 2 comments · Opened Sep 17, 2026
requesting-code-review: Claude Code rewrites the example's `awk '{print $1}'` when the skill gets arguments Open

Difficulty 1/5 Under an hour Newbie friendliness 91/100

obra/superpowers#2311 · 1 comment · Opened Sep 17, 2026
SessionStart hooks (run-hook.cmd, session-start) fail when PATH is broken: dirname/cat/bash not found Open

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

obra/superpowers#2310 · Opened Sep 17, 2026
writing-plans: self-review misses task-state/DAG closure in executable plans Open

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

obra/superpowers#2309 · 5 comments · Opened Sep 17, 2026
Claude Code instructions have the repo path wrong? Open

Difficulty 1/5 Under an hour Newbie friendliness 92/100

obra/the-elements-of-style#18 · Opened Sep 17, 2026
SDD helper scripts prompt for an app on Windows when invoked from PowerShell Open

Difficulty 3/5 1-2 days Newbie friendliness 74/100

obra/superpowers#2307 · Opened Sep 16, 2026
subagent-driven-development: review-package renders commit subjects only, so the task reviewer reports commit-body disclosures as undisclosed changes Open

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

obra/superpowers#2298 · 1 comment · Opened Sep 13, 2026
subagent-driven-development: the ledger records no in-flight task, so an outage mid-task re-dispatches work that is already committed Open

Difficulty 2/5 Half a day Newbie friendliness 78/100

obra/superpowers#2293 · Opened Sep 12, 2026
writing-skills: GREEN measures compliance, not outcome Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

obra/superpowers#2292 · 1 comment · Opened Sep 12, 2026
executing-plans assumes every plan produces code changes in a git-tracked project Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

obra/superpowers#2290 · Opened Sep 12, 2026
writing-plans: Execution Handoff question always blocks, even when the choice is obvious Open

Difficulty 3/5 1-2 days Newbie friendliness 55/100

obra/superpowers#2289 · 1 comment · Opened Sep 12, 2026
verification-before-completion: the skill requires fresh evidence but never asks where the evidence came from Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

obra/superpowers#2286 · 5 comments · Opened Sep 11, 2026
writing-plans: expected values in verification steps are asserted, not produced — and can be contradicted by the plan's own text Open

Difficulty 2/5 1-3 hours Newbie friendliness 75/100

obra/superpowers#2285 · Opened Sep 11, 2026
subagent-driven-development: implementer dispatches are gated on nothing — briefs get referenced unwritten and todo state never updates Open

Difficulty 3/5 1-2 days Newbie friendliness 78/100

obra/superpowers#2282 · Opened Sep 11, 2026
Recovery path still can't converge: #95's probe reports a package healthy when its declared entry point is missing, and a truncated tree makes the repair install fail rather than repair Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

obra/episodic-memory#170 · Opened Sep 11, 2026
systematic-debugging ships its pressure-test fixtures inside the skill directory; they open with "This is a real scenario. You must choose and act" Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 76/100

obra/superpowers#2277 · 2 comments · Opened Sep 10, 2026
Onboarding Open

Difficulty 3/5 1-2 days Newbie friendliness 55/100

obra/winpepper#59 · Opened Sep 9, 2026
MCP per-server tool policy: 'deny' is inert — only 'disable' has any effect Open

Difficulty 5/5 Over a week Newbie friendliness 45/100

obra/lace#400 · Opened Sep 9, 2026
SDD: Approve + Important triggers mandatory re-review loop Open

enhancement

Difficulty 4/5 3-5 days Newbie friendliness 48/100

obra/superpowers#2273 · Opened Sep 9, 2026
writing-plans: `Files:` labels are undefined, so `Test:` gets used for both new and existing test files Open

Difficulty 1/5 Under an hour Newbie friendliness 85/100

obra/superpowers#2268 · Opened Sep 8, 2026
subagent-driven-development: the progress ledger records completion but not cross-task discoveries, so a usage-limit interruption loses what earlier tasks learned Open

Difficulty 4/5 3-5 days Newbie friendliness 58/100

obra/superpowers#2267 · Opened Sep 8, 2026
verification-before-completion: a commit message is a claim about the diff, and "add one more" breaks sibling count assertions Open

Difficulty 3/5 1-2 days Newbie friendliness 52/100

obra/superpowers-marketplace#75 · Opened Sep 7, 2026
writing-plans: anchor edit instructions to content, and two failure modes specific to test code written inside a plan Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

obra/superpowers-marketplace#74 · Opened Sep 7, 2026
subagent-driven-development: the setup scripts derive context from the environment, and fail silently off the happy path Open

Difficulty 4/5 3-5 days Newbie friendliness 52/100

obra/superpowers-marketplace#73 · Opened Sep 7, 2026
Fixes keep creating new bugs because no skill requires tracing what a fix changes Open

Difficulty 3/5 1-2 days Newbie friendliness 78/100

obra/superpowers#2266 · Opened Sep 6, 2026
7 additive rules for superpowers skills (from real-session postmortems) Open

Difficulty 3/5 1-2 days Newbie friendliness 64/100

obra/superpowers#2264 · 1 comment · Opened Sep 6, 2026
Self-references point to nonexistent obra/elements-of-style (missing the-) Open

Difficulty 2/5 1-3 hours Newbie friendliness 35/100

obra/the-elements-of-style#14 · Opened Sep 5, 2026
receiving-code-review: "grep codebase for actual usage" can propose deleting live code (an empty result is not proof of absence) Open

Difficulty 1/5 Under an hour Newbie friendliness 88/100

obra/superpowers#2261 · Opened Sep 5, 2026
Codex reference assumes spawn capabilities unavailable in an observed desktop session Open

Difficulty 1/5 1-3 hours Newbie friendliness 88/100

obra/superpowers#2260 · Opened Sep 5, 2026
Performance: experimental.chat.messages.transform O(n) scan on every agent step causes >180s timeout on 1000+ message sessions Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 55/100

obra/superpowers#2254 · Opened Sep 4, 2026
subagent-driven-development: Finish deletes the only record of deferred findings — parked/deferred items need a durable export Open

Difficulty 3/5 1-2 days Newbie friendliness 72/100

obra/superpowers#2253 · Opened Sep 4, 2026
Superpowers 6.3.0 OpenCode plugin causes startup hang on Windows with OpenCode 1.18.27 Open

Difficulty 4/5 3-5 days Newbie friendliness 52/100

obra/superpowers#2252 · Opened Sep 4, 2026
Antigravity (agy): plugin hooks.json fails to parse — the using-superpowers bootstrap never loads Open

antigravity bug hooks

Difficulty 4/5 3-5 days Newbie friendliness 50/100

obra/superpowers#2247 · Opened Sep 2, 2026
Delegation skills: four dispatch checks that silently fail without them (base commit, spawned model, enumerable scope, parallel-dispatch isolation) Open

enhancement skills subagents worktrees

Difficulty 4/5 3-5 days Newbie friendliness 45/100

obra/superpowers#2245 · Opened Sep 2, 2026
Reviewer template: harden against hallucinated cross-domain references (cheap model tiers) Open

enhancement skills subagents

Difficulty 1/5 1-3 hours Newbie friendliness 88/100

obra/superpowers#2243 · 2 comments · Opened Sep 2, 2026
SDD scripts (task-brief/review-package) crash on greenfield Task 1 — no git repo yet Open

bug subagents

Difficulty 2/5 1-3 hours Newbie friendliness 76/100

obra/superpowers#2242 · 1 comment · Opened Sep 2, 2026
skills/writing-plans + executing-plans: plans assume application code, and a verification can silently check a different object than the operation it guards Open

enhancement plans skills

Difficulty 4/5 3-5 days Newbie friendliness 45/100

obra/superpowers#2241 · Opened Sep 1, 2026
skills/brainstorming: the one-question rule is a proxy for a quality property, and a named vendor is an unmarked claim Open

brainstorming enhancement skills

Difficulty 4/5 3-5 days Newbie friendliness 52/100

obra/superpowers#2240 · 1 comment · 1 reaction · Opened Sep 1, 2026
skills/writing-plans + executing-plans: a guard a later plan should relax needs "narrow it", not "delete it" Open

enhancement plans skills

Difficulty 3/5 1-2 days Newbie friendliness 68/100

obra/superpowers#2234 · 1 comment · Opened Aug 31, 2026
skills/writing-skills: moving content breaks relative links silently, and `Triggers on:` makes the frontmatter invalid YAML Open

enhancement skills

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

obra/superpowers#2233 · 2 comments · Opened Aug 31, 2026
skills/systematic-debugging: sizing a probe for intermittent behaviour, and preserving evidence before reproducing Open

enhancement skills

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

obra/superpowers#2232 · Opened Aug 31, 2026
skills/verification-before-completion: `git checkout` in a verified-red loop destroys uncommitted work Open

enhancement skills

Difficulty 3/5 1-2 days Newbie friendliness 68/100

obra/superpowers#2231 · 1 comment · Opened Aug 31, 2026
skills/test-driven-development: three gaps — tests as the deliverable, detector suites, and closing deferred work Open

enhancement skills tdd

Difficulty 3/5 1-2 days Newbie friendliness 68/100

obra/superpowers#2230 · 1 comment · Opened Aug 31, 2026
Skills that script multi-branch git workflows never establish a remote-safety boundary, shared branches (production, dev) were unintentionally rewritten across three projects Open

enhancement skills worktrees

Difficulty 4/5 3-5 days Newbie friendliness 48/100

obra/superpowers#2219 · Opened Aug 28, 2026
`finishing-a-development-branch` can silently delete an SDD workspace: ignored files don't make a worktree dirty Open

bug skills subagents worktrees

Difficulty 4/5 3-5 days Newbie friendliness 48/100

obra/superpowers#2207 · Opened Aug 26, 2026
Bounded tasks fill the main session context Open

brainstorming bug codex subagents

Difficulty 4/5 3-5 days Newbie friendliness 45/100

obra/superpowers#2203 · 2 comments · Opened Aug 25, 2026
dispatching-parallel-agents: a dispatched agent can re-delegate and return a status promise, silently losing the lane Open

enhancement skills subagents

Difficulty 1/5 Under an hour Newbie friendliness 88/100

obra/superpowers#2202 · Opened Aug 25, 2026
OpenCode: bootstrap not injected in non-interactive `opencode run` sessions (skills still register) Open

bug hooks needs-repro-case opencode

Difficulty 3/5 1-2 days Newbie friendliness 68/100

obra/superpowers#2197 · 1 comment · Opened Aug 23, 2026

Showing the newest 100

This page lists what was indexed most recently. Advanced filter has the whole inventory, narrowed by language, difficulty and how long a task takes.

Open advanced filter

obra

Showing the newest 100

Get new issues in your inbox