verify-pstack-learn
Verify the pstack learn terminal dashboard after catalog, history, keyboard, rendering, or refresh changes.
Skill by philrenaud
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/philrenaud-verify-pstack-learn
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: data
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/verify-pstack-learn
What's inside
- Skill name
verify-pstack-learn- Description
- Verify the pstack learn terminal dashboard after catalog, history, keyboard, rendering, or refresh changes. Drives the real TUI in an isolated pseudo-terminal.
- License
- MIT
- Instructions
- 29 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- files: referenced but missing: scripts/verify-learn.py
Files (4)
- SKILL.md
- README.md · features/
- discover.md · features/
- evidence.md · features/
SKILL.md (first lines)
# Verify pstack learn ## Launch From this repository root, run `bun install --frozen-lockfile --cwd tools/learn`. The app entry point is `./learn`. Each verification drive owns a separate pseudo-terminal and temporary SQLite database. ## Doctor Run `./learn --help` and `./learn --snapshot`. The snapshot must display `pstack learn` and the catalog. A missing real history database is an explicitly labeled UNKNOWN state, not proof of zero use. ## Drive Run `python3 scripts/verify-learn.py --evidence .audit/learn-terminal.txt`. The helper launches the real OpenTUI executable, searches with raw keyboard input, appends a skill load from a second SQLite writer, refreshes, opens recent examples and exact original context, rejects synthetic tool-echo text, opens help, resizes, opens narrow details, prints an invocation, and tests Ctrl-C while searching. Its terminal screen decoder handles OpenTUI's incremental ANSI updates. Run `bun run --cwd tools/learn test` and `bun run --cwd tools/learn typecheck` for evidence classification and catalog changes. Read [features/README.md](features/README.md) for coverage. ## Evidence The PTY helper asserts user-visible output and terminal restoration, then saves raw terminal output to `.audit/learn-terminal.txt`. The file must survive cleanup. A snapshot alone does not prove keyboard interaction. Skill loads and file consultations must remain separate. Test data never counts as live user history. ## Cleanup The helper terminates only its own child processes and deletes its own temporary database after each drive. It preserves the evidence path even on failure. Do not kill OpenCode or modify its database. ## Helpers `scripts/verify-learn.py` runs with Python 3 and its standard PTY/SQLite libraries. No tmux or external service is required.
From philrenaud/pstack-opencode, MIT.
More from philrenaud/pstack-opencode
- 0.575score
how
philrenaud
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
SkillAFreshness: A★ 2Claude Code +9 - 0.575score
architect
philrenaud
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
SkillAFreshness: A★ 2Claude Code +9 - 0.575score
poteto-mode
philrenaud
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
SkillAFreshness: A★ 2Claude Code +9 - 0.575score
create-verification-skill
philrenaud
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
SkillAFreshness: A★ 2Claude Code +9 - 0.575score
interrogate
philrenaud
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillAFreshness: A★ 2Claude Code +9 - 0.570score
blast-radius
philrenaud
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of…
SkillAFreshness: A★ 2Claude Code +9 - 0.570score
arena
philrenaud
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
SkillAFreshness: A★ 2Claude Code +9 - 0.567score
no-comments
philrenaud
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
SkillAFreshness: A★ 2Claude Code +9 - 0.529score
maintain-verification-skill
philrenaud
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature…
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 10, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/philrenaud/pstack-opencode
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from philrenaud
- 0.575score
how
philrenaud
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
SkillAFreshness: A★ 2Claude Code +9 - 0.575score
architect
philrenaud
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
SkillAFreshness: A★ 2Claude Code +9 - 0.575score
poteto-mode
philrenaud
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
SkillAFreshness: A★ 2Claude Code +9 - 0.575score
create-verification-skill
philrenaud
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
SkillAFreshness: A★ 2Claude Code +9 - 0.575score
interrogate
philrenaud
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillAFreshness: A★ 2Claude Code +9 - 0.570score
blast-radius
philrenaud
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of…
SkillAFreshness: A★ 2Claude Code +9
Cite this page
verify-pstack-learn skill. Agent Mart. https://agentmart.dev/skills/philrenaud-verify-pstack-learn (last updated 2026-10-24)