Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mickpletcher/AI-Skills --skill astrophotography-processinggit clone --depth 1 https://github.com/mickpletcher/AI-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mickpletcher/ai-skills/astrophotography-processing)<a href="https://agentmods.dev/skills/mickpletcher/ai-skills/astrophotography-processing"><img src="https://agentmods.dev/badge/skills/mickpletcher/ai-skills/astrophotography-processing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mickpletcher/ai-skills/astrophotography-processing"><img src="https://agentmods.dev/badge/skills/mickpletcher/ai-skills/astrophotography-processing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.01644 |
| Opus 5.5 | $0.00018 | $0.00658 |
| Sonnet 5.5 | $0.00009 | $0.00329 |
| Haiku 4.5 | $0.00004 | $0.00164 |
Grade A, and why
astrophotography-processing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Astrophotography Processing
Purpose
Help users produce technically sound astrophotography results while preserving original data, metadata, and reproducibility.
Use When
Use this skill only when context clearly indicates astrophotography or night-sky imaging workflows.
Trigger examples:
- Telescope/lens star fields, deep-sky objects, Milky Way, comet, lunar/planetary/solar data
- Calibration frames, stacking, registration, gradient removal, color calibration
- FITS/XISF/RAW subs, linear masters, rejection maps, dithering, deconvolution
- PixInsight, Siril, Astro Pixel Processor, DeepSkyStacker, StarNet, StarXTerminator, WinJUPOS, Python astro pipelines
Do Not Use When
- General photo editing requests without astronomy context
- Fashion, portrait, product, wedding, travel edits not involving night-sky capture workflows
Operating Mode
Choose one primary mode and label it in the response:
- Diagnosis: inspect visible or file-based issues and identify likely causes.
- Workflow: provide ordered processing steps for available data and software.
- Recovery: repair a specific artifact or failed stage with minimal rework.
- Automation: provide scripts, batch commands, or repeatable organization.
- Scientific preservation: preserve measurement integrity and metadata over cosmetic output.
Evidence Rules
- Separate observed issues from likely causes.
- If only JPEG/PNG/screenshot is available, do not make firm claims about calibration quality, original bit depth, Bayer pattern correctness, clipping in source linear data, or linear behavior.
- Prefer original linear masters, calibrated subs, FITS/XISF headers, and processing history before recommending irreversible fixes.
- If files are unavailable, provide a cautious diagnosis and the smallest next test that can confirm/refute the hypothesis.
Minimal Questions Policy
Keep intake lightweight.
- Ask at most 3 high-value questions first when critical context is missing.
- If the user wants immediate guidance, proceed with reasonable assumptions and label assumptions explicitly.
- Do not dump the full intake checklist unless requested.
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- astrophotography-processing.skill 32 KB
- completedchanges.md 582 B
- future-upgrades.md 638 B
- README.md 2.0 KB
- references/app-dss-photoshop.md 1.3 KB
- references/calibration.md 1.9 KB
- references/comets-mosaics-dualband.md 1.2 KB
- references/milky-way-landscape.md 904 B
- references/pixinsight.md 1.6 KB
- references/planetary-lunar-solar.md 1.2 KB
- references/siril.md 1.2 KB
- references/troubleshooting.md 2.0 KB
- scripts/fits_audit.py 3.4 KB runs code
- scripts/image_stats_preview.py 3.6 KB runs code
- templates/processing-log.md 640 B
- upgrades.md 858 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago Changed · +14 lines cd7cb402c584
- 1mo ago First seen · 151 lines · 44 tokens per session scan A aaa8693ee1f4
astrophotography-processing is a skill published in the GitHub repository mickpletcher/AI-Skills (20 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,644 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
godot-optimization
Use when optimizing Godot games — profiler, draw calls, physics tuning, memory management, and common bottlenecks.
grant-writing
This skill should be used when the user asks to "write a grant proposal", "draft specific aims", "write a research strategy", "create an NIH proposal", "create an NSF proposal", "write a significance section", "write an innovation section", "write an approach section", "draft a DP2 essay", "write an R01", "write an…
lit-review
Use this skill for "literature review workflow", "multi-phase lit review", "direction paper", "review paper protocol", "strand-based literature review", "citation-grounded review", "systematic lit review with paper cards", "build a lit review corpus", "lit review pipeline", "orchestrate a literature review", "research…
manuscript-formatting
Use this skill for "format manuscript", "prepare for submission", "journal formatting", "Word", "DOCX", "reference DOCX", "LaTeX template", "submission checklist", "format references", "BibTeX", "author guidelines", "page limits", "format for Nature", "format for IEEE", or when the user wants to format a manuscript…
ai-full-figure
Use this skill when the user asks to "generate an AI figure", "make an AI-generated figure", "make a poster figure", "make a presentation figure", "generate a figure with AI", "generate figure panels with Codex", "make a multi-panel AI figure", "AI background for a figure", or wants a pictorial figure or panel (brain…
bids-conversion
Use this skill for "convert to BIDS", "BIDS format", "create BIDS dataset", "BIDS sidecar", "participants.tsv", "events.tsv", "EEG BIDS", "EMG BIDS", "MEG BIDS", "fMRI BIDS", "BIDS validator", "channel locations", "electrode positions", "BIDS metadata", or when the user wants to convert neuroscience data to Brain…