Extracting Requirements
prime-radiant-inc/iterative-development
Reads human-written spec documents and produces per-epic requirement files with proof obligations plus behavior scenarios with stable IDs, using parallel chunked extraction.
Caveman-style compression for conducty orchestration artifacts — subagent prompt text, plan note prompt blocks, prompt log entries, checkpoint notes.
Install Conducty Terse
$ npx skills add robertbarclayy/conducty --skill conducty-terse -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install robertbarclayy/conducty conducty-terse --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/robertbarclayy/conducty.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/conducty-terse .claude/skills/conducty-terse && 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 "conducty-terse" agent skill from https://github.com/robertbarclayy/conducty/tree/main/skills/conducty-terse into .claude/skills/conducty-terse/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conducty-terse", 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/robertbarclayy/conducty/tree/main/skills/conducty-terseType 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 robertbarclayy/conducty --skill conducty-terse -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install robertbarclayy/conducty conducty-terse --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/robertbarclayy/conducty.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/conducty-terse .agents/skills/conducty-terse && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "conducty-terse" agent skill from https://github.com/robertbarclayy/conducty/tree/main/skills/conducty-terse into .agents/skills/conducty-terse/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conducty-terse", 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 robertbarclayy/conducty --skill conducty-terse -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install robertbarclayy/conducty conducty-terse --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/robertbarclayy/conducty.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/conducty-terse .cursor/skills/conducty-terse && 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 "conducty-terse" agent skill from https://github.com/robertbarclayy/conducty/tree/main/skills/conducty-terse into .cursor/skills/conducty-terse/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conducty-terse", 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/robertbarclayy/conducty.git --path skills/conducty-terse--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 robertbarclayy/conducty --skill conducty-terse -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install robertbarclayy/conducty conducty-terse --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/robertbarclayy/conducty.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/conducty-terse .gemini/skills/conducty-terse && 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 "conducty-terse" agent skill from https://github.com/robertbarclayy/conducty/tree/main/skills/conducty-terse into .gemini/skills/conducty-terse/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conducty-terse", 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 robertbarclayy/conducty conducty-terseInstalls 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 robertbarclayy/conducty --skill conducty-terse -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/robertbarclayy/conducty.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/conducty-terse .github/skills/conducty-terse && 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 "conducty-terse" agent skill from https://github.com/robertbarclayy/conducty/tree/main/skills/conducty-terse into .github/skills/conducty-terse/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conducty-terse", 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 robertbarclayy/conducty --skill conducty-terse -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install robertbarclayy/conducty conducty-terse --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/robertbarclayy/conducty.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/conducty-terse .opencode/skills/conducty-terse && 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 "conducty-terse" agent skill from https://github.com/robertbarclayy/conducty/tree/main/skills/conducty-terse into .opencode/skills/conducty-terse/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conducty-terse", 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
conducty-terse- GitHub stars
- 176
- Token cost
- ~1.6k tokens
- SKILL.md length
- 765 words
- Files
- 1
- Skills in repo
- 20
- Repo updated
- First seen
- Licence
- MIT
At a glance
Caveman-style compression for conducty orchestration artifacts — subagent prompt text, plan note prompt blocks, prompt log entries, checkpoint notes.
- User says conducty-terse
- SKILL.md covers Scope — what gets compressed, Compression rules, Examples and Auto-clarity (override terse), plus 3 more sections
- Calls pnpm
- Compress prompts
What it does
Conducty Terse is an agent skill from robertbarclayy/conducty. Caveman-style compression for conducty orchestration artifacts — subagent prompt text, plan note prompt blocks, prompt log entries, checkpoint notes. Cuts token waste in the orchestration layer where "prompt quality is leverage" already demands tight signal-to-noise. Use when user says "conducty-terse", "terse mode", "compress prompts", "tight prompts", or invokes /conducty-terse. Does NOT change subagent output, code, commits, acceptance criteria, no-go zones, or verification commands — those stay verbatim.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Subagents and User stories. The repository describes itself as: Stop context-switching. Start batch-planning. Conducty replaces the fragmented cycle of plan → prompt → wait → get distracted → review → fix → repeat with advanced batch planning. The licence is MIT.
When your agent uses it
- User says conducty-terse
- Compress prompts
- Invokes /conducty-terse
Example prompts
- “prompt quality is leverage”
- “conducty-terse”
- “terse mode”
- “/conducty-terse”
What it can do on your machine
Read from SKILL.md and the folder at commit 64aefd5. 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
Shell commands in SKILL.md call:
pnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.
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
Conducty Terse loads about 1.6k tokens when it runs. Until then it costs about 132 tokens; SKILL.md has 765 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 robertbarclayy/conducty at commit 64aefd5, republished under its MIT licence (© robertbarclayy). 765 words, ~1,646 tokens.
Download SKILL.mdSave it as
.claude/skills/conducty-terse/SKILL.md (or your agent's skills folder).- name
- conducty-terse
- description
- Caveman-style compression for conducty orchestration artifacts — subagent prompt text, plan note prompt blocks, prompt log entries, checkpoint notes. Cuts token waste in the orchestration layer where "prompt quality is leverage" already demands tight signal-to-noise. Use when user says "conducty-terse", "terse mode", "compress prompts", "tight prompts", or invokes /conducty-terse. Does NOT change subagent output, code, commits, acceptance criteria, no-go zones, or verification commands — those stay verbatim.
- aliases
- conducty-terse, terse
- tags
- conducty/skill, conducty/discipline
Conducty Terse — Compression for Orchestration Artifacts
Caveman energy applied to conducty surface area. Prompts dispatched to subagents, prompt blocks in plan notes, entries in [[Prompt Log]], checkpoint notes — these are the artifacts where extra words cost twice: they bloat your orchestrator window AND every dispatched subagent's window.
This skill is the mechanical follow-through to the Conducty principle that prompt quality is leverage. Smaller prompts mean larger usable subagent context windows, which means more room for actual code, file reads, and verification output.
Scope — what gets compressed
| Artifact | Apply terse? | Reason |
|---|---|---|
| Subagent prompt text (Task tool input) | Yes | Every word costs once in your context, again in the subagent's |
| Plan note prompt blocks | Yes | Re-read on every dispatch; bloat compounds |
[[Prompt Log]] entries | Yes | Append-only; the file grows forever |
| Checkpoint notes | Yes | Read by [[conducty-improve]] later |
| Orchestrator status updates to user | Yes | Match the user's caveman mode if active |
| Subagent reasoning / output | No | Subagents write in their own register |
| Acceptance criteria | No | Precision > brevity |
| No-go zones | No | Ambiguity = scope creep |
| Verification commands | No | Exact strings, never paraphrase |
| Error messages quoted | No | Verbatim or useless |
| Code, commits, PRs | No | Same boundary as caveman |
| Security warnings, destructive op confirmations | No | Auto-clarity rule |
Compression rules
Drop: articles (a/an/the), filler (just/really/simply/basically/actually), pleasantries (sure/certainly/please/happy to), hedging (might/perhaps/it seems), narrative throat-clearing ("In order to...", "It is important to note that...", "The reason we're doing this is..."), redundant restatement of plan context the subagent already has.
Keep exact: technical terms, file paths, error strings, command invocations, model names (haiku/sonnet/opus), type signatures, link targets ([[wikilink]]), acceptance criteria text, no-go zone text, verification command strings.
Style: Fragments OK. Short synonyms (big not extensive, fix not implement a solution for). Bullets over paragraphs when both work. Pattern: [artifact] [action] [reason]. [next step].
Examples
Subagent prompt — bloated
Hello! For this task, I'd like you to please go ahead and refactor the user authentication middleware located in
src/middleware/auth.tsso that it uses the newverifyTokenfunction fromsrc/lib/jwt.tsinstead of the legacydecodeTokenfunction. The reason we're doing this refactor is that the legacy function does not handle expired tokens correctly, which has been causing issues in production for the past few weeks. Please make sure that all existing tests continue to pass after your changes.
Subagent prompt — terse
Refactor
src/middleware/auth.tsto useverifyTokenfromsrc/lib/jwt.ts. Replace alldecodeTokencalls.Reason: legacy
decodeTokenmishandles expired tokens (prod incident).Acceptance criteria: [verbatim from plan, do not paraphrase]
No-go zones: [verbatim from plan, do not paraphrase]
Verify:
pnpm test src/middleware/auth.test.tsTime budget: 20m. Model: sonnet.
Prompt Log entry — bloated
2026-04-27 14:32 — Prompt P3 from Plan 2026-04-27 1400 [Auth Refactor] completed successfully on the first attempt. Verification ran clean and the spec reviewer found no compliance issues. The implementation took roughly 18 minutes, which was within the 20-minute time budget.
Show full SKILL.md (301 more words)Show less
Prompt Log entry — terse
2026-04-27 14:32 · P3 [[Plan 2026-04-27 1400 Auth Refactor]] · DONE · 1st attempt · spec-review clean · 18m / 20m budget
Checkpoint note — bloated
Group A finished. All four prompts completed without issues. The first-attempt pass rate was 100%, with no retries needed and no prompts blocked. Overall the group went smoothly and we're ready to proceed to Group B.
Checkpoint note — terse
Group A · 4/4 done · 1st-attempt 100% · 0 retries · 0 blocked · proceed Group B
Auto-clarity (override terse)
Always write normal prose when:
- Acceptance criteria — copy verbatim from plan, never compress
- No-go zones — copy verbatim from plan, never compress
- Security warnings or destructive operation confirmations
- Multi-step protocols where fragment order risks misread (e.g. compact-resume sequence)
- Error messages quoted from logs
- Verification command strings
Resume terse after the precision-required part is done.
Persistence
Active when the skill is invoked. Stays active until the user says "stop terse", "normal mode", or "stop conducty-terse". No drift mid-session. If unsure whether terse still applies, default to active.
Interaction with caveman
caveman covers user-facing chat compression. conducty-terse covers conducty artifacts written to the vault or dispatched to subagents.
- Both can be active simultaneously — they target different surfaces.
- If both active and they conflict:
conducty-tersewins for vault and subagent artifacts;cavemanwins for user-facing chat. - Turning one off does not turn the other off.
Principles
- Compression is downstream of clarity — never sacrifice acceptance criteria precision for terseness
- Exact strings are sacred — file paths, errors, commands, link targets, acceptance criteria, no-go zones never paraphrase
- Terse the prose, not the spec — narrative shrinks, structure stays
- Vault artifacts are read many times — every word saved pays compound interest across plan, checkpoint, review, improve, and future plans loading the same context
- Subagents inherit your terseness — a tight prompt teaches the subagent the register; a bloated prompt invites a bloated reply
© robertbarclayy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/conducty-terse of robertbarclayy/conducty.
Open the folder on GitHubat commit 64aefd5
Compare with similar skills
Conducty Terse 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 |
|---|---|---|---|---|---|---|
| Conducty Terse this skillrobertbarclayy/conducty | 176 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Extracting Requirementsprime-radiant-inc/iterative-development | 181 | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| Skill Studioglebis/claude-skills | 391 | — | ~2.8k | Automated safety check: Pass | MIT | |
| Idea ValidatorMathews-Tom/armory | 329 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Coherence AuditorGoogleChrome/modern-web-guidance-src | 1.1k | — | ~864 | Automated safety check: Pass | Apache-2.0 | |
| Agent RelayAgentWorkforce/relay | 869 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Skill Studio
glebis/claude-skills
Interview-driven automation design tool. An agent skill from glebis/claude-skills.
Idea Validator
Mathews-Tom/armory
Orchestrates business idea validation via parallel sub-agents: Lean Canvas, JTBD, market/competitive/feasibility research, SWOT/PESTLE, and a weighted scorecard with verdict.
Coherence Auditor
GoogleChrome/modern-web-guidance-src
Run a document coherence, link integrity, and git repository status audit across repository markdown files using a dedicated subagent.
Agent Relay
AgentWorkforce/relay
A skill your agent uses when you need Codex to coordinate multiple agents through Agent Relay for peer-to-peer messaging, lead/worker handoffs, or shared status tracking across sub-agents and…
Gen Plan
alibaba/atrex-kernel-agent
Generate a structured implementation plan from an evidence draft.
More from robertbarclayy/conducty
All 20 skills in this repoConducty Checkpoint
robertbarclayy/conducty
Quality gate between parallelization groups. An agent skill from robertbarclayy/conducty.
Conducty Code Review
robertbarclayy/conducty
Standalone post-implementation code review across a whole branch or PR.
Conducty Context
robertbarclayy/conducty
Ingest a project directory into the Obsidian vault as a linked context sub-graph — Architecture, Conventions, Invariants, Hotspots, Tests, Glossary, plus per-bounded-context module notes.
Conducty Debug
robertbarclayy/conducty
Leverage-point analysis for failed prompts. An agent skill from robertbarclayy/conducty.
Conducty Execute
robertbarclayy/conducty
Dispatches Claude Code Task subagents to run prompts from a vault plan note.
Conducty Improve
robertbarclayy/conducty
End-of-plan improvement kata. An agent skill from robertbarclayy/conducty.
Related
Questions about Conducty Terse
What does Conducty Terse do?
Caveman-style compression for conducty orchestration artifacts — subagent prompt text, plan note prompt blocks, prompt log entries, checkpoint notes. Conducty Terse is an agent skill from robertbarclayy/conducty. Caveman-style compression for conducty orchestration artifacts — subagent prompt text, plan note prompt blocks, prompt log entries, checkpoint notes.
When should I use Conducty Terse?
Conducty Terse fits situations like: user says conducty-terse; compress prompts; invokes /conducty-terse.
How do I install Conducty Terse in Claude Code?
Run `npx skills add robertbarclayy/conducty --skill conducty-terse -a claude-code`. Or copy the skill folder (skills/conducty-terse in robertbarclayy/conducty) into .claude/skills/conducty-terse in your project. Claude Code loads it when a task matches its description.
How do I install Conducty Terse in Codex?
Run `npx skills add robertbarclayy/conducty --skill conducty-terse -a codex`. Or copy the skill folder (skills/conducty-terse in robertbarclayy/conducty) into .agents/skills/conducty-terse in your project. Codex loads it when a task matches its description.
Can I use Conducty Terse 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 robertbarclayy/conducty --skill conducty-terse -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/conducty-terse, .gemini/skills/conducty-terse, .github/skills/conducty-terse and .opencode/skills/conducty-terse in your project.
What does Conducty Terse need to run?
Going by SKILL.md and its folder, Conducty Terse needs the command-line tools its instructions call (pnpm).
Does Conducty Terse 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 Conducty Terse 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 Conducty Terse use?
Conducty Terse 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 Conducty Terse use?
About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Conducty Terse?
Skills that share tags, products or a category with Conducty Terse: Extracting Requirements (prime-radiant-inc/iterative-development, 181 stars), Skill Studio (glebis/claude-skills, 391 stars), Idea Validator (Mathews-Tom/armory, 329 stars) and Coherence Auditor (GoogleChrome/modern-web-guidance-src, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Conducty Terse?
robertbarclayy (a GitHub user) maintains it in robertbarclayy/conducty, which has 176 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on June 19, 2026.
Source: robertbarclayy/conducty on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.