Conversation
Co-authored-by: Eric Elliott <support@paralleldrive.com>
SKILL.md specifies default: 10. The command quick-reference incorrectly stated default: 5. Co-authored-by: Eric Elliott <support@paralleldrive.com>
Removed the steps section detailing the process for ideation and evaluation.
…encies - Command file: use H1 with /aidd-rtc name, matching aidd-fix and aidd-churn patterns - Command file: delegate option details to SKILL.md instead of duplicating them - Command file: add missing [prompt] arg to usage line - Command file: use /aidd-please shorthand instead of full path - SKILL.md: fix --depth= to --depth N for consistency with README and command docs - SKILL.md: remove trailing blank lines - Regenerate index.md files to include aidd-rtc entries
There was a problem hiding this comment.
Pull request overview
Adds the new aidd-rtc skill (Reflective Thought Composition) and wires it into the commands/skills indexes for discovery and use.
Changes:
- Introduces
ai/skills/aidd-rtc/SKILL.mddefining the RTC pipeline plus options (--compact,--depth). - Adds human-facing docs (
ai/skills/aidd-rtc/README.md) and a command card (ai/commands/aidd-rtc.md). - Updates
ai/skills/index.mdandai/commands/index.mdto include the new skill/command.
Reviewed changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated 4 comments.
Show a summary per file
| File | Description |
|---|---|
| ai/skills/index.md | Adds aidd-rtc entry to the skills index. |
| ai/skills/aidd-rtc/SKILL.md | Defines the RTC skill, including Commands/Options and the 6-stage pipeline. |
| ai/skills/aidd-rtc/README.md | Provides user-facing documentation and usage examples. |
| ai/commands/index.md | Adds /aidd-rtc to the commands index. |
| ai/commands/aidd-rtc.md | Adds the /aidd-rtc command card pointing to the skill file. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| 🗜️🐘🤔💭 --compact Compress thinking: SPR🧠 associative. Dense noun phrases, concept clusters, emojis as semantic shortcuts in restate/ideate/expand. Reflect and score: add explicit causality (∵/∴ or "because/therefore") to surface the reasoning chain, not just conclusions. Every internal stage: load-bearing tokens only, no filler. 💬Respond = full natural language, standalone, structured. | ||
| --depth -d [1..10] (default: 10) Response density. 1 = a few words per step, 10 = several bullet points per step. |
There was a problem hiding this comment.
In the Options block, the option syntax is harder to parse/copy than other skills. Consider matching the established format from aidd-please (e.g., start the line with the flag name, and document the short alias/argument consistently as --depth N | -d N [1..10] (default: 10)), rather than prefixing the flag with emojis and omitting the N placeholder.
| 🗜️🐘🤔💭 --compact Compress thinking: SPR🧠 associative. Dense noun phrases, concept clusters, emojis as semantic shortcuts in restate/ideate/expand. Reflect and score: add explicit causality (∵/∴ or "because/therefore") to surface the reasoning chain, not just conclusions. Every internal stage: load-bearing tokens only, no filler. 💬Respond = full natural language, standalone, structured. | |
| --depth -d [1..10] (default: 10) Response density. 1 = a few words per step, 10 = several bullet points per step. | |
| --compact Compress thinking: SPR🧠 associative. Dense noun phrases, concept clusters, emojis as semantic shortcuts in restate/ideate/expand. Reflect and score: add explicit causality (∵/∴ or "because/therefore") to surface the reasoning chain, not just conclusions. Every internal stage: load-bearing tokens only, no filler. 💬Respond = full natural language, standalone, structured. | |
| --depth N | -d N [1..10] (default: 10) Response density. 1 = a few words per step, 10 = several bullet points per step. |
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 5fa0f28. Configure here.
Updated the description of the Reflective Thought Composition (RTC) and modified the commands and options sections for clarity.
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 5 out of 5 changed files in this pull request and generated no new comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Split from PR #94. One skill per PR per project standards.
What
Adds aidd-rtc (Reflective Thought Composition) — a structured deep-thinking primitive for agents.
RTC is a 6-stage reasoning pipeline: restate → ideate → reflect → expand → score → respond. It forces agents to show work at each stage before delivering a final answer, improving reasoning quality for complex decisions, design evaluation, and deep analysis.
Files
ai/skills/aidd-rtc/SKILL.md— Full skill specification with frontmatter, pipeline definition, options, and step descriptionsai/skills/aidd-rtc/README.md— Human-readable documentation: what, why, and command referenceai/commands/aidd-rtc.md— Quick-reference command cardOptions
--compact— Dense internal reasoning (SPR-style), full natural language only in final respond step--depth N(1–10, default: 10) — Controls detail level per reasoning stageReview notes
validate-skill(44 body lines, 597 body tokens, well within thresholds)--depthdefault inconsistency: command file originally said 5, SKILL.md source of truth says 10 — corrected to 10Review fixes applied
/aidd-rtcname to matchaidd-fixandaidd-churnconventions[prompt]arg to command usage lineai/skills/aidd-please/SKILL.mdto/aidd-pleaseshorthand--depth=to--depth Nfor consistency with README and command docsai/skills/index.mdandai/commands/index.mdnow include aidd-rtc