<feed xmlns='http://www.w3.org/2005/Atom'>
<title>superpowers.git/tests/explicit-skill-requests, branch codex/shell-lint-script</title>
<subtitle>Agentic skills framework and development workflow
</subtitle>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/'/>
<entry>
<title>Tighten cross-platform tool references</title>
<updated>2026-05-14T00:46:28+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@primeradiant.com</email>
</author>
<published>2026-05-14T00:29:04+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=d4d99117f2fa3c59052563efe9248a597a5f78f1'/>
<id>d4d99117f2fa3c59052563efe9248a597a5f78f1</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>tests: remove run-claude-describes-sdd.sh (covered by drill mid-conversation-skill-invocation)</title>
<updated>2026-05-06T22:47:39+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-05-06T19:25:46+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=f10cddac0d2c9cebc9bfb674cc1d02cb22ecbdc2'/>
<id>f10cddac0d2c9cebc9bfb674cc1d02cb22ecbdc2</id>
<content type='text'>
Subagent verification: every bash assertion (Skill tool invoked +
specific skill name 'subagent-driven-development' loaded after the
agent describes it conversationally in turn 1) maps to the drill
scenario's skill-called assertion + criteria paragraph requiring
the skill to fire in direct response to the second user message.
Drill additionally asserts tool-called Agent (subagent dispatch)
which is stricter than the bash test.

Other runners in tests/explicit-skill-requests/ (haiku, multiturn,
extended-multiturn) and their prompt files are preserved — they
have no drill coverage and exercise different behaviors.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Subagent verification: every bash assertion (Skill tool invoked +
specific skill name 'subagent-driven-development' loaded after the
agent describes it conversationally in turn 1) maps to the drill
scenario's skill-called assertion + criteria paragraph requiring
the skill to fire in direct response to the second user message.
Drill additionally asserts tool-called Agent (subagent dispatch)
which is stricter than the bash test.

Other runners in tests/explicit-skill-requests/ (haiku, multiturn,
extended-multiturn) and their prompt files are preserved — they
have no drill coverage and exercise different behaviors.
</pre>
</div>
</content>
</entry>
<entry>
<title>fix: use portable shebang #!/usr/bin/env bash in all shell scripts</title>
<updated>2026-03-15T18:38:04+00:00</updated>
<author>
<name>jesse</name>
<email>jesse@magic-kingdom</email>
</author>
<published>2026-03-15T18:38:00+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=addfe8511a0543d04b30ff50b7e5f6c88e998368'/>
<id>addfe8511a0543d04b30ff50b7e5f6c88e998368</id>
<content type='text'>
Replace #!/bin/bash with #!/usr/bin/env bash in 13 scripts. The
hardcoded path fails on NixOS, FreeBSD, and macOS with Homebrew bash.
#!/usr/bin/env bash is the portable POSIX-friendly alternative.

Tested on Linux and Windows (Git Bash + CMD). macOS is the primary
beneficiary since Homebrew installs bash to /opt/homebrew/bin/bash.

Based on #700, closes #700.

Co-Authored-By: Claude Opus 4.6 &lt;noreply@anthropic.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Replace #!/bin/bash with #!/usr/bin/env bash in 13 scripts. The
hardcoded path fails on NixOS, FreeBSD, and macOS with Homebrew bash.
#!/usr/bin/env bash is the portable POSIX-friendly alternative.

Tested on Linux and Windows (Git Bash + CMD). macOS is the primary
beneficiary since Homebrew installs bash to /opt/homebrew/bin/bash.

Based on #700, closes #700.

Co-Authored-By: Claude Opus 4.6 &lt;noreply@anthropic.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>refactor: restructure specs and plans directories</title>
<updated>2026-03-06T21:01:31+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-01-22T21:55:26+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=f57638a74759376871509ccf080e606f62052f1b'/>
<id>f57638a74759376871509ccf080e606f62052f1b</id>
<content type='text'>
- Specs (brainstorming output) now go to docs/superpowers/specs/
- Plans (writing-plans output) now go to docs/superpowers/plans/
- User preferences for locations override these defaults
- Update all skill references and test files

Co-Authored-By: Claude Opus 4.5 &lt;noreply@anthropic.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
- Specs (brainstorming output) now go to docs/superpowers/specs/
- Plans (writing-plans output) now go to docs/superpowers/plans/
- User preferences for locations override these defaults
- Update all skill references and test files

Co-Authored-By: Claude Opus 4.5 &lt;noreply@anthropic.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Strengthen using-superpowers for explicit skill requests</title>
<updated>2025-12-27T04:41:22+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-12-27T04:41:22+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=3dac35e0b35c2fbe4222ba825381eb764d65f085'/>
<id>3dac35e0b35c2fbe4222ba825381eb764d65f085</id>
<content type='text'>
Addresses failure mode where Claude skips skill invocation even when
user explicitly requests it by name (e.g., "subagent-driven-development,
please").

Skill changes:
- "Check for skills" → "Invoke relevant or requested skills"
- "BEFORE ANY RESPONSE" → "BEFORE any response or action"
- Added reassurance that wrong skill invocations are okay
- New red flag: "I know what that means"

Tests:
- New test suite for explicit skill requests
- Single-turn and multi-turn scenarios with --continue
- Tests with haiku model and user CLAUDE.md
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Addresses failure mode where Claude skips skill invocation even when
user explicitly requests it by name (e.g., "subagent-driven-development,
please").

Skill changes:
- "Check for skills" → "Invoke relevant or requested skills"
- "BEFORE ANY RESPONSE" → "BEFORE any response or action"
- Added reassurance that wrong skill invocations are okay
- New red flag: "I know what that means"

Tests:
- New test suite for explicit skill requests
- Single-turn and multi-turn scenarios with --continue
- Tests with haiku model and user CLAUDE.md
</pre>
</div>
</content>
</entry>
</feed>
