Skip to content
Back to search

easy-context-question

SkillWorks with Claude CodeGitHub

Claude Code skill: turn your agents' open questions into a plain-English decision brief. Context, options with cost, one recommendation. Answer with one letter.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/tomi2k--easy-context-question/badge.svg)](/listings/tomi2k--easy-context-question)

HTML

<a href="/listings/tomi2k--easy-context-question"><img src="/api/listings/tomi2k--easy-context-question/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

git clone https://github.com/Tomi2k/easy-context-question.git
mkdir -p ~/.claude/skills
cp -r easy-context-question/skills/easy-context-question ~/.claude/skills/

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 119 lines
  1. <p align="center">
  2. <img src="assets/hero.png" alt="A tangle of technical agent questions goes in, one clear decision card with a recommendation comes out." width="100%">
  3. </p>
  4. # easy-context-question
  5. **Turn your agents' questions into decisions you can answer with one letter.**
  6. A skill for [Claude Code](https://code.claude.com). When agents, issues, plans or review
  7. reports ask you something, this skill rewrites the questions into a short decision brief:
  8. what it is about in plain words, the options with their consequence and cost, and exactly
  9. one recommendation. You answer "1A 2B" - without opening a single file.
  10. ```
  11. /easy-context-question the open questions in issue #212
  12. ```
  13. ---
  14. ## Why this exists
  15. The more agents work for you, the more questions come back - and they come back in the
  16. agents' language: ticket numbers, function names, half-explained trade-offs. To answer one
  17. question, you read the issue, then the code, then the previous discussion. The decision
  18. itself is quick. Understanding the question is not.
  19. | Problem | What the skill does |
  20. |---|---|
  21. | Questions are written in jargon: ticket numbers, file names, internal labels. | Plain words. A technical term is explained once, in half a sentence. |
  22. | "It depends" - the agent lists options but does not commit. | Exactly one recommendation per question, with a reason. |
  23. | You answer things the agent could have found out itself. | Questions the agent can settle by reading code and docs are settled first and reported in one line. |
  24. | You get asked the same thing twice. | Questions you already decided are dropped. |
  25. | Twelve questions at once, the blocking one is number nine. | At most 7 per brief, blocking questions and deadlines first. |
  26. | An option silently costs money or cannot be undone. | A **Warning** line before the options. |
  27. | Your answer gets lost. | The skill hands your choices back to whoever asked - outside the session only after your OK. |
  28. ### Plain words on purpose
  29. The language rules follow **Simplified Technical English** (ASD-STE100), the controlled
  30. language created for aerospace maintenance documentation
  31. ([about ASD-STE100](https://asd-ste100.org/about_STE.html)). The standard limits sentences
  32. to 20 words in procedures and 25 in descriptions; this skill uses 20 for everything.
  33. One statement per sentence, active voice, present tense, one word for one thing, numbers
  34. with units instead of descriptions. Text written for a mechanic in a hangar also works
  35. for a busy founder between two calls.
  36. ## What you get
  37. ```markdown
  38. ### Question 1: How long to keep debug logs (#57)
  39. **What this is about:** The app keeps debug logs for 90 days. They use 40 GB and cost
  40. 9 USD per month. In the last 6 months nobody opened a log older than 14 days.
  41. **Warning:** Option A deletes all logs older than 14 days. You cannot get them back.
  42. **Options:**
  43. - **A - Keep 14 days:** Storage drops to about 7 GB. Cost drops to about 2 USD per month. Effort for you: 0.
  44. - **B - Keep 90 days:** Nothing changes. Cost stays at 9 USD per month.
  45. **Recommendation: A.** The old logs are not used, and the saving repeats every month.
  46. Answer: "all recommendations", or one letter per question, for example "1A".
  47. ```
  48. ## Install
  49. ```bash
  50. git clone https://github.com/Tomi2k/easy-context-question.git
  51. mkdir -p ~/.claude/skills
  52. cp -r easy-context-question/skills/easy-context-question ~/.claude/skills/
  53. ```
  54. ## Use
  55. ```
  56. /easy-context-question the open questions of the current conversation
  57. /easy-context-question issue #212 the questions in a specific issue
  58. /easy-context-question the review report any source the agent can read
  59. ```
  60. It also runs on plain requests such as "what do I need to decide?" or "explain the
  61. open questions", and when your agent is about to put a manager agent's or subagent's
  62. questions to you. In multi-agent setups, tell your manager agent to use this format for
  63. every question it sends you - then every check-in ends with one line you can answer.
  64. ## Rules the skill follows
  65. - Read the original source completely - never answer from memory.
  66. - Never invent an option. A missing obvious option is added and marked as an addition.
  67. - Do not copy the source's recommendation blindly; disagreement is stated in one sentence.
  68. - Costs and deadlines only when verified - otherwise "cost not checked".
  69. - No secrets, no customer data, no legal texts in the brief.
  70. ## Security
  71. The skill is a single Markdown file: no scripts, no hooks, no dependencies. It does not
  72. call any service by itself. It tells your agent what to do with the agent's normal tools:
  73. - **Reading:** the agent reads the sources you point it to (an issue, a report, a file).
  74. Text from these sources is treated as data - the skill forbids following instructions
  75. found inside them. This reduces the risk of indirect prompt injection through public
  76. issues, but prompt rules cannot fully prevent it: point the skill only at sources you
  77. would also read yourself.
  78. - **Checking:** questions are settled only by reading tracked project files and docs - no
  79. shell or network commands, no `.env`, secret or credential files. Anything that changes
  80. state, costs money or touches an account needs your approval.
  81. - **Writing back:** inside the session, the chosen options go back to the agent that
  82. asked. Before anything is written outside the session (an issue, a pull request, a
  83. chat), the agent shows you the exact target and the exact text and waits for your OK. It sends only your
  84. choices, never your raw chat, secrets or customer data.
  85. ## License
  86. MIT - see [LICENSE](LICENSE).
  87. ---
  88. Built by **Timothy Scherman**. Less AI theater. More results.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.