Diagnosing Superpowers Sessions
jnMetaCode/superpowers-zh
Investigates what went wrong in a superpowers session by reading its transcript, reports findings with path and line citations, and can draft a GitHub issue or redacted bundle.
Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.
Install Diagnosing Superpowers Sessions
$ npx skills add obra/superpowers --skill diagnosing-superpowers -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install obra/superpowers diagnosing-superpowers --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/obra/superpowers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/diagnosing-superpowers .claude/skills/diagnosing-superpowers && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "diagnosing-superpowers" agent skill from https://github.com/obra/superpowers/tree/main/skills/diagnosing-superpowers into .claude/skills/diagnosing-superpowers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diagnosing-superpowers", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/obra/superpowers/tree/main/skills/diagnosing-superpowersType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add obra/superpowers --skill diagnosing-superpowers -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install obra/superpowers diagnosing-superpowers --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/obra/superpowers.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/diagnosing-superpowers .agents/skills/diagnosing-superpowers && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "diagnosing-superpowers" agent skill from https://github.com/obra/superpowers/tree/main/skills/diagnosing-superpowers into .agents/skills/diagnosing-superpowers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diagnosing-superpowers", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add obra/superpowers --skill diagnosing-superpowers -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install obra/superpowers diagnosing-superpowers --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/obra/superpowers.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/diagnosing-superpowers .cursor/skills/diagnosing-superpowers && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "diagnosing-superpowers" agent skill from https://github.com/obra/superpowers/tree/main/skills/diagnosing-superpowers into .cursor/skills/diagnosing-superpowers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diagnosing-superpowers", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/obra/superpowers.git --path skills/diagnosing-superpowers--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add obra/superpowers --skill diagnosing-superpowers -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install obra/superpowers diagnosing-superpowers --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/obra/superpowers.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/diagnosing-superpowers .gemini/skills/diagnosing-superpowers && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "diagnosing-superpowers" agent skill from https://github.com/obra/superpowers/tree/main/skills/diagnosing-superpowers into .gemini/skills/diagnosing-superpowers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diagnosing-superpowers", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install obra/superpowers diagnosing-superpowersInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add obra/superpowers --skill diagnosing-superpowers -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/obra/superpowers.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/diagnosing-superpowers .github/skills/diagnosing-superpowers && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "diagnosing-superpowers" agent skill from https://github.com/obra/superpowers/tree/main/skills/diagnosing-superpowers into .github/skills/diagnosing-superpowers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diagnosing-superpowers", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add obra/superpowers --skill diagnosing-superpowers -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install obra/superpowers diagnosing-superpowers --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/obra/superpowers.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/diagnosing-superpowers .opencode/skills/diagnosing-superpowers && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "diagnosing-superpowers" agent skill from https://github.com/obra/superpowers/tree/main/skills/diagnosing-superpowers into .opencode/skills/diagnosing-superpowers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diagnosing-superpowers", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
diagnosing-superpowers- GitHub stars
- 297k
- Used in
- 3 other repos
- Token cost
- ~1.7k tokens
- SKILL.md length
- 929 words
- Files
- 20 (incl. references)
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- MIT
At a glance
Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.
- Works in 7 steps: Problem intake. Ask one question at a… → Locate. Resolve each session to verified… → Triage. Read the region around the… → …
- A Superpowers session repeated work or ignored the plan
- SKILL.md covers Overview, Workflow, Quick reference and Hard rules, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
When a session showed repeated work, ignored plans, stumbles, slowness or high cost, the agent works out with you what went wrong and reports it with evidence. It does not diagnose Superpowers itself; whoever triages the bundle or issue decides whether anything changes. Every finding must cite `path:line`, and every number must come from the transcript or a command the agent ran, never from memory.
The workflow runs through problem intake, asking one question at a time; locating the session and subagent transcripts using `references/session-discovery.md` and filling a case file under `~/.superpowers/diagnosing-superpowers/`; triage, with one analyst subagent per dimension in parallel (skill timeline, plan adherence, repeated work, stumbles, quality evidence, request conflicts, cost and time), discarding findings without citations; and a written report. If the report points to a bug, the agent searches existing GitHub issues and drafts a new one from a template. Reference files cover redaction and context safety. The excerpt is truncated.
When your agent uses it
- A Superpowers session repeated work or ignored the plan
- Finding out why a session took too long or cost too much
- A skill that should have fired did not
- Building a bug report for the Superpowers maintainers from a session
Example prompts
- “My last Superpowers session kept redoing the same step. Work out why.”
- “Why was this session so expensive? Check the transcript and cite evidence.”
- “Turn the session I just finished into a bug report for the Superpowers maintainers.”
Requirements
- Access to the session transcripts on disk
- GitHub issue search, if you want a bug report
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Problem intake. Ask one question at a time until you can write a
- Locate. Resolve each session to verified absolute filesystem paths using
- Triage. Read the region around the reported problem yourself. Then
- Report. Fill every section of templates/report.md in order, write
- GitHub issues — when report §7 says possible or likely, or your
- Export — only when your partner asks for a bundle; never build one
- Similar sessions — when asked. Turn confirmed findings into a
What it can do on your machine
Read from SKILL.md and the folder at commit 8ca22db. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Diagnosing Superpowers Sessions loads about 1.7k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 100 tokens; SKILL.md has 929 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from obra/superpowers at commit 8ca22db, republished under its MIT licence (© obra). 929 words, ~1,721 tokens.
Download SKILL.mdSave it as
.claude/skills/diagnosing-superpowers/SKILL.md (or your agent's skills folder). This skill also uses 19 other files; get the full folder from GitHub.- name
- diagnosing-superpowers
- description
- Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.
Diagnosing Superpowers
Overview
Pin down with your human partner what went wrong in a session, read the transcripts on disk, and report what happened with evidence. You report; you do not diagnose superpowers. Whoever triages the bundle or the issue decides whether superpowers changes.
Core principle: Every finding cites path:line. No citation, no
finding. Every number comes from the transcript or from a command you ran,
never from memory.
Workflow
Create a todo per step. Steps 5–7 run only on their stated condition.
- Problem intake. Ask one question at a time until you can write a statement naming the session(s), the turn range if known, what your partner expected, what happened, and the observable they care about (wall-clock, tokens, repeated actions, one specific action). "It took too long" is a complaint, not a problem statement. Note whether the goal is a superpowers bug report.
- Locate. Resolve each session to verified absolute filesystem paths using
references/session-discovery.md. Confirm a past session by quoting its first prompt and timestamp, and list every candidate you rejected with the reason, or "none". Enumerate subagent transcripts. Create~/.superpowers/diagnosing-superpowers/<session-id>/, tell your partner the path, and filltemplates/case.mdthere, following its provenance rules for environment and skill observations. - Triage. Read the region around the reported problem yourself. Then
dispatch one analyst subagent per dimension in parallel, each given the
case file path,
prompts/analyst-common.md, and one dimension file fromprompts/:skill-timeline.md,plan-adherence.md,repeated-work.md,stumbles.md,quality-evidence.md,request-conflicts.md,cost-and-time.md. Split a dimension by turn range when the transcript is long. Discard any returned finding withoutpath:line. - Report. Fill every section of
templates/report.mdin order, write it to the workspace, show it, and give the path. Check what cited content actually proves and preserve the supporting case; a symlink alias is not a redundant copy. - GitHub issues — when report §7 says possible or likely, or your
partner asks. Search open and closed issues for the symptoms per
references/github-issues.md. Show matches and suggest adding the report to the closest. If none match, filltemplates/issue.md, write it to the workspace, show the exact text, and create the issue only after approval.ghcannot attach files; if a bundle exists, give your partner its path to attach in the browser. - Export — only when your partner asks for a bundle; never build one
unprompted. If the intake goal was a bug report, say once that a
scrubbed bundle is available on request, then wait. Ask the redaction
level, stating what each includes: skeleton (no tool-result bodies),
evidence (bodies only for cited events), full. Build the bundle per
templates/bundle-README.md, dispatchprompts/scrub.md, thenprompts/scrub-audit.md, repeating both until the audit returns CLEAN. Complete the bundle template's evidence check and reconciliation before showing the final scrub log, file list, and privacy and evidence outcomes. Archive (zip -rortar -czf) only after approval. With the archive path, state what it contains, point at the scrub log for replacements, and say scrubbing can miss things: they must review every file before sharing. - Similar sessions — when asked. Turn confirmed findings into a
signature, list candidates by mtime and size, find marker line numbers,
dispatch
prompts/similar-session.mdper candidate in parallel, and append report §9.
Show full SKILL.md (401 more words)Show less
Quick reference
All seven analysts always run. This table says which region to read yourself in step 3 and which findings to lead with in the verdict.
| Complaint | Read first, lead with |
|---|---|
| "It took too long" | cost-and-time, stumbles |
| "Why did it do this extra work?" | repeated-work, plan-adherence |
| "Why is it so expensive?" | cost-and-time |
| "What the hell is it doing?" (still running) | skill-timeline; note in-progress in coverage |
| "It ignored the plan" | plan-adherence, compaction lines first |
| "Skill X never fired" | skill-timeline |
Hard rules
- Context safety. One transcript line can be a megabyte. Follow
references/context-safety.mdon every session file, every time. - Read-only. Never modify, move, or delete a session file.
- Exact paths to subagents. A subagent's "current session" is its own. Pass absolute paths and ids.
- Human prompts only. Hook output, system reminders, and tool results are not your partner's words. In a subagent transcript, "user" is the parent agent.
- No superpowers diagnosis. Report §7 states involvement and stops. Never name a defect in a skill or propose a change. Your partner pressing for a fix does not waive this; point at the issue step and mention that a bundle is available on request. No advice to your partner either.
- Approval gates. No archive before your partner has seen the scrub log and file list. No issue or comment before they approve the exact text.
- Intake before analysis. Nothing in steps 2–7 starts until your partner has answered. If they are away, write the questions and stop. A statement you reconstructed for them is not an answer. An already-scoped request — one specific event, what is running now, or the analysis to run — is itself the statement: answer it, then ask. A whole-session "why" is a complaint.
Red Flags
| Thought | Reality |
|---|---|
| "The problem is obvious, skip intake" | The problem statement scopes everything. Ask. |
| "They're away, so I'll reconstruct the statement" | You cannot reconstruct what they wanted. Write the questions and stop. |
| "I'll sweep everything now and ask at the end" | An unscoped sweep spends their budget on the wrong question. Ask first. |
| "They want a bug report, so I'll build the bundle now" | The bundle is their session data, packaged. Build it only when they ask for it. |
| "Small, targeted edit, no restructuring needed" | Not your call, however small. Report the evidence; the triager decides. |
| "The price per token is well known" | Numbers you did not compute from the transcript are invented. Cite or drop. |
© obra, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 19 other files (references) in skills/diagnosing-superpowers of obra/superpowers.
- SKILL.md
- prompts/analyst-common.md
- prompts/cost-and-time.md
- prompts/plan-adherence.md
- prompts/quality-evidence.md
- prompts/repeated-work.md
- prompts/request-conflicts.md
- prompts/scrub-audit.md
- prompts/scrub.md
- prompts/similar-session.md
- prompts/skill-timeline.md
- prompts/stumbles.md
- references/context-safety.md
- references/github-issues.md
- references/redaction-policy.md
- references/session-discovery.md
- templates/bundle-README.md
- templates/case.md
- … and 2 more
Open the folder on GitHubat commit 8ca22db
Used in 3 other repositories
We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in obra/superpowers, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Diagnosing Superpowers Sessions next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Diagnosing Superpowers Sessions this skillobra/superpowers | 297k | 3 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Diagnosing Superpowers SessionsjnMetaCode/superpowers-zh | 8.3k | — | ~858 | Automated safety check: Pass | MIT | |
| OpenROAD Bug FixerThe-OpenROAD-Project/OpenROAD | 3.2k | — | ~784 | Automated safety check: Pass | BSD-3-Clause | |
| Octocode Code Researchbgauryy/octocode | 949 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Triagebot Action Bug Triagewithastro/astro | 63k | — | ~639 | Automated safety check: Pass | Custom licence | |
| Issue TracerZaxbyHub/opencode-swarm | 493 | — | ~4.4k | Automated safety check: Pass | MIT |
Similar skills
OpenROAD Bug Fixer
The-OpenROAD-Project/OpenROAD
Fixes an OpenROAD bug from a GitHub issue or error code: finds the root cause, implements the fix, adds a regression test and prepares a signed-off commit.
Octocode Code Research
bgauryy/octocode
Researches code with evidence: traces callers, imports and cross-repo links, diagnoses failures and reports findings with exact file and line references and a confidence label.
- Official
Triagebot Action Bug Triage
withastro/astro
Takes a bug report for the triagebot-action GitHub Action through reproduction, root-cause diagnosis, an intended-behavior check and a fix attempt.
Issue Tracer
ZaxbyHub/opencode-swarm
Drives a bug report from validation and root-cause tracing through a critic-reviewed plan, an approved minimal fix and a PR-ready closure, never merging without recorded human approval.
Prp Debug
Wirasm/prp
Diagnoses a bug, error, stack trace, regression, or unexplained behavior and publishes the evidence-backed root cause to GitHub.
More from obra/superpowers
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
Related
Works with
Categories
Questions about Diagnosing Superpowers Sessions
What does Diagnosing Superpowers Sessions do?
Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers. When a session showed repeated work, ignored plans, stumbles, slowness or high cost, the agent works out with you what went wrong and reports it with evidence. It does not diagnose Superpowers itself; whoever triages the bundle or issue decides whether anything changes.
When should I use Diagnosing Superpowers Sessions?
Diagnosing Superpowers Sessions fits situations like: A Superpowers session repeated work or ignored the plan; finding out why a session took too long or cost too much; A skill that should have fired did not; building a bug report for the Superpowers maintainers from a session.
How do I install Diagnosing Superpowers Sessions in Claude Code?
Run `npx skills add obra/superpowers --skill diagnosing-superpowers -a claude-code`. Or copy the skill folder (skills/diagnosing-superpowers in obra/superpowers) into .claude/skills/diagnosing-superpowers in your project. Claude Code loads it when a task matches its description.
How do I install Diagnosing Superpowers Sessions in Codex?
Run `npx skills add obra/superpowers --skill diagnosing-superpowers -a codex`. Or copy the skill folder (skills/diagnosing-superpowers in obra/superpowers) into .agents/skills/diagnosing-superpowers in your project. Codex loads it when a task matches its description.
Can I use Diagnosing Superpowers Sessions in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add obra/superpowers --skill diagnosing-superpowers -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/diagnosing-superpowers, .gemini/skills/diagnosing-superpowers, .github/skills/diagnosing-superpowers and .opencode/skills/diagnosing-superpowers in your project.
What does Diagnosing Superpowers Sessions need to run?
SKILL.md names no scripts, command-line tools or credentials: Diagnosing Superpowers Sessions is instructions for the agent only. Our summary lists: Access to the session transcripts on disk; GitHub issue search, if you want a bug report.
Does Diagnosing Superpowers Sessions access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Diagnosing Superpowers Sessions safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Diagnosing Superpowers Sessions use?
Diagnosing Superpowers Sessions is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Diagnosing Superpowers Sessions use?
About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.7k tokens, read only when the agent opens those files.
What are the alternatives to Diagnosing Superpowers Sessions?
Skills that share tags, products or a category with Diagnosing Superpowers Sessions: Diagnosing Superpowers Sessions (jnMetaCode/superpowers-zh, 8.3k stars), OpenROAD Bug Fixer (The-OpenROAD-Project/OpenROAD, 3.2k stars), Octocode Code Research (bgauryy/octocode, 949 stars) and Triagebot Action Bug Triage (withastro/astro, 63k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Diagnosing Superpowers Sessions?
obra (a GitHub user) maintains it in obra/superpowers, which has 296,672 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 9, 2026.
Source: obra/superpowers on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.